Import Security Issue From Md

import-security-issue-from-md

This skill is the batch on-ramp of the security-issue handling process for the case where the security team has a markdown file containing one or more pre-formatted security findings — typically the output of an AI security review run against an <upstream> branch, or a third-party scanner exporting in a similar shape. It parses each finding in the file and creates one <tracker> tracking issue per finding, landing them in Needs triage so the standard validity discussion (Step 3 of README.md) can run.

It is the third on-ramp variant alongside the two existing import skills:

Golden rule — every finding lands as Needs triage. A markdown file (especially an AI-generated one) is a proposal of findings, not an assessment. Each tracker created by this skill must go through the same Step 3 validity discussion as a Gmail- imported tracker. The skill must not pre-assess findings based on their **Severity:** tag, must not skip the validity step for findings tagged HIGH, and must not auto-allocate CVEs.

Golden rule — confidentiality. The input markdown file is private security-team material. Treat it the same as <security-list> content per the Confidentiality of <tracker> rule: paste verbatim into the (private) tracker is fine; never paste into a public surface — not into <upstream>, not into a public GHSA, not into any comment on a public repo. The ## Location URL fields commonly point at public branches / files; that is fine to render as-is in the tracker (the URL is already public), but do not propagate the surrounding security framing to the public surface the URL points at.

Golden rule — propose every finding individually before applying. Even when the input is a 50-finding file, the skill surfaces a proposal table listing every finding and waits for explicit confirmation. The default disposition mirrors import-security-issue: import all unless rejected upfront (skip N to drop a specific candidate). A bare go / proceed / yes, all imports every non-rejected candidate. The skill must still render each candidate in the proposal so the user can scan and override.

Prerequisites

Before running, the skill needs:

• gh CLI authenticated with collaborator access to <tracker>. The skill calls gh issue create, gh search issues, and gh issue edit.
• Project-board write access for the addProjectV2ItemById / updateProjectV2ItemFieldValue mutations from tools/github/project-board.md.
• Read access to the markdown file — the skill expects an absolute path or a path relative to cwd.

No Gmail, no PonyMail, no <upstream> access. There is no inbound thread to read and no reporter to draft a reply to.

See Prerequisites for running the agent skills in README.md for overall setup.

Step 0 — Pre-flight check

Before parsing the file, verify:

1. gh is authenticated and has access. Run gh api repos/<tracker> --jq .name; on 401 / 403 / 404, stop and tell the user to log in or get added.
2. The input path is readable. Read the file. If it does not exist or is empty, stop and surface a one-line ask for the correct path.
3. The file is markdown of the expected shape. Quick sanity check: at least one # (title) heading and at least one **Severity:** metadata line. If neither is present, stop and surface: "This does not look like a findings file. Expected format: per-finding # Title, ## Details, ## Location, ## Impact, ## Reproduction steps, ## Recommended fix sections, then a **Severity:** … **Status:** … **Category:** … **Repository:** … **Date created:** … metadata block; blocks separated by --- on their own line."

If any check fails, do not proceed.

Step 1 — Parse the file into findings

The expected per-finding shape:

# <Title — one short imperative phrase>

## Details
<Multi-paragraph technical description. May reference file paths,
line numbers, function names. Often the longest section.>

## Location
[<file/line label>](<URL into the public source>)

## Impact
<One sentence. The threat actor's gain: arbitrary code execution,
data exfiltration, privilege escalation, etc.>

## Reproduction steps
1. <numbered list>
2. ...

## Recommended fix
<Suggested remediation. Free-form prose.>

---
**Severity:** HIGH|MEDIUM|LOW|UNKNOWN
**Status:** Open
**Category:** <free-text — Insecure Deserialization / RCE, SSRF, Broken Access Control, etc.>
**Repository:** <owner>/<repo>
**Branch:** <ref>
**Date created:** YYYY-MM-DD

Findings are separated by --- on its own line (with blank lines around it). The metadata block at the end of each finding is itself preceded by ---.

Parsing recipe:

1. Read the whole file.
2. Split on the regex (?m)^---\s*$ to get raw blocks.
3. Drop blocks that are pure whitespace.
4. Group adjacent blocks: a "finding" is the block ending in the **Severity:** metadata line, plus the immediately preceding block (which carries # Title through ## Recommended fix). Equivalently: walk blocks pairwise, treating (narrative-block, metadata-block) as one finding.
5. For each finding, extract the per-section payload:
   • # Title → the line after # until newline.
   • Each ## <Section> → everything until the next ## heading or the end of the narrative block.
   • Metadata: per-line **Field:** value extraction.
6. Validate per finding:
   • # Title is non-empty.
   • **Severity:** is one of HIGH, MEDIUM, LOW, UNKNOWN (case-insensitive); anything else → record as UNKNOWN and surface a one-line warning.
   • **Repository:** matches <owner>/<repo> shape; if absent, fall back to <upstream> (from <project-config>/project.md) and warn.
   • ## Details, ## Impact, and ## Reproduction steps are present and non-empty. If any are missing, surface a warning but do not skip the finding (the importer can fill in _No response_ for the corresponding tracker body field).

Record into the observed-state bag a list of findings, each with:

• index (1-based, matches the proposal table number).
• title (raw).
• details, location_url, location_label, impact, repro_steps, recommended_fix (string payloads).
• severity, status, category, repository, branch, date_created (metadata).

Step 2 — Duplicate-tracker guard

For each parsed finding, search <tracker> for an existing tracker with overlapping content so the skill does not silently land a duplicate:

gh search issues "<title-keyword>" --repo <tracker> --json number,title,state,url

Pick <title-keyword> as the most distinctive 3-5 word substring from the finding's title (drop common security words like "in", "the", "via"). Hits with high title overlap, or hits whose body mentions the same ## Location URL, are surfaced inline in the proposal as "possible duplicate of <tracker>#NNN" — they do not auto-skip; the user decides during Step 4.

The duplicate guard is a soft signal, not a hard gate. Many AI scans re-discover findings already tracked; surfacing the overlap lets the user skip N for those candidates without parsing the full file by hand.

Step 3 — Build proposed tracker contents (per finding)

For each finding, prepare the tracker fields:

3a — Title

The tracker title is the finding's # Title with the standard [ Security Report ] prefix prepended (per the issue-template convention; see tools/github/issue-template.md):

[ Security Report ] <finding title>

The title is left otherwise untouched — this skill does not run the title-normalisation cascade (that lives in allocate-cve, by which point the validity of the report is established).

3b — Issue body

Map markdown sections to the standard <tracker> issue-template body fields (per tools/github/issue-template.md; the role → concrete-name mapping comes from <project-config>/project.md):

Also append a "Recommended fix (per the source markdown)" collapsible block at the end of the body. The recommended fix is useful triage context but does not belong in any of the standard template fields; a <details> block at the end of the body keeps it out of the per-field surgery the other skills perform.

3c — Labels

Apply at creation:

• needs triage — every finding from this skill enters the standard validity-assessment flow.
• security issue — required for the <tracker> Auto-add to project workflow filter (is:issue label:"security issue"); without it the issue will not appear on the board.

Do not apply a scope label. Scope labels are assigned at Step 5 of the handling process, after the validity assessment.

3d — Project board

Target column: Needs triage. The Auto-add to project workflow adds the issue automatically once security issue is applied; the skill still calls updateProjectV2ItemFieldValue to set the Status to Needs triage explicitly, so the column lands deterministically (per the orphan-issue path in tools/github/project-board.md).

3e — Status-rollup comment

The first entry on the tracker's status rollup. Shape per tools/github/status-rollup.md:

<!-- <tracker> status rollup v1 — all bot-authored status updates fold into this single comment. -->
<details><summary><YYYY-MM-DD> · @<author-handle> · Import from markdown (<basename>, finding <K>/<N>)</summary>

**Imported from markdown file `<basename>` on <YYYY-MM-DD>** (severity: `<severity>`, category: `<category>`).

This tracker was deliberately opened by the security team from a batch findings file. The validity of the report has **not** been assessed yet — the tracker landed in the `Needs triage` column accordingly. Standard Step 3 discussion applies.

**Source:** `<basename>` (finding `<K>` of `<N>` in the file).
**Location reference:** <location_url>
**Severity (from source):** `<severity>` (informational; CVSS scoring happens at allocation).
**Category (from source):** `<category>` (informational; CWE assignment happens at allocation).
</details>

Zero-whitespace rules from status-rollup.md apply: no leading spaces on any line inside the <details> block, exactly one blank line after <summary>…</summary>, exactly one blank line before </details>.

Step 4 — Surface the proposal and wait for confirmation

Render a single proposal covering every parsed finding:

<file-basename> — N findings parsed.

| # | Severity | Category                       | Title                                              | Possible duplicate |
|---|----------|--------------------------------|----------------------------------------------------|--------------------|
| 1 | HIGH     | Insecure Deserialization / RCE | Arbitrary callable invocation during serialized…  | <tracker>#NNN      |
| 2 | HIGH     | Insecure Deserialization / RCE | Arbitrary import in custom deadline-reference…    | (none)             |
| 3 | MEDIUM   | Server-Side Request Forgery    | SSRF from API server via worker-supplied hostname | (none)             |
| 4 | MEDIUM   | Broken access control          | Import-error per-DAG authorization check is a no-op | (none)             |
| 5 | LOW      | Open redirect                  | Open-redirect validator accepts backslash-prefix… | (none)             |
| 6 | LOW      | Xss                            | DAG-author-controlled hrefs rendered without…     | (none)             |

Default disposition: import all 6 as `Needs triage`.
Reply with one of:
  - `go` / `proceed` / `yes, all`     — import every finding above.
  - `skip 4`                          — drop finding 4; import the rest.
  - `skip 4,6`                        — drop multiple.
  - `cancel` / `none`                 — bail; no trackers created.

Confirmation forms:

• go / proceed / yes, all — import every finding.
• skip <N> (or skip <N>,<M>,…) — drop the listed findings; import the remaining ones. The dropped findings get no tracker (no audit-trail draft, no follow-up — the markdown file itself is the audit trail).
• cancel / none / hold off — bail; no trackers created.

If a possible-duplicate flag is non-empty for a finding, the user typically skips it after a quick eyeball of the cited tracker; the skill should not auto-skip on duplicate signal alone.

The proposal is a single round-trip even for a 50-finding file. The skill must not stream per-finding confirmations.

Step 5 — Apply (per kept finding, in order)

For each finding the user did not skip, run Steps 5a-5f sequentially. The whole batch is a serial loop, not parallel — per-finding gh calls and project-board mutations interleave with GitHub rate limits cleanly when serialised.

5a — Create the tracker via gh api

Bypasses the form so the Security mailing list thread required-field check does not fire. Same pattern as import-security-issue-from-pr's Step 7a.

Write the body to a temp file (per finding):

cat > /tmp/import-md-<basename>-<index>-body.md <<'EOF'
### The issue description

> **Imported from markdown file `<basename>` (finding <K>/<N>)** — there is no inbound `security@` report; the markdown sections below are the verbatim source.

**Details:**

<## Details payload, verbatim>

**Impact:**

<## Impact payload, verbatim>

**Reproduction steps:**

<## Reproduction steps payload, verbatim>

### Short public summary for publish

_No response_

### Affected versions

`<owner>/<repo>` @ `<branch>` — versions to be confirmed during triage.

### Security mailing list thread

N/A — imported from markdown file `<basename>`; no security@ thread.

### Public advisory URL

_No response_

### Reporter credited as

_No response_

### PR with the fix

<location_url if it points at a <upstream> PR, else _No response_>

### Remediation developer

_No response_

### CWE

<category from metadata; free-text — actual CWE assigned at triage>

### Severity

<severity from metadata>

### CVE tool link

_No response_

<details><summary>Recommended fix (per the source markdown)</summary>

<## Recommended fix payload, verbatim>
</details>
EOF

Create:

gh api repos/<tracker>/issues \
  -f title='[ Security Report ] <finding title>' \
  -F body=@/tmp/import-md-<basename>-<index>-body.md \
  --jq '.number, .node_id, .html_url'

Capture number, node_id, html_url from the response.

5b — Apply labels

gh issue edit <new-issue-number> \
  --repo <tracker> \
  --add-label 'needs triage' \
  --add-label 'security issue'

No scope label, no pr created / pr merged — those come later in the lifecycle.

5c — Pin to the Needs triage board column

Run the orphan-issue path from tools/github/project-board.md:

gh api graphql -f query='
  mutation($pid:ID!,$nid:ID!) {
    addProjectV2ItemById(input: { projectId: $pid, contentId: $nid }) {
      item { id }
    }
  }' \
  -F pid=<project-node-id> \
  -F nid=<issue-node-id> \
  --jq '.data.addProjectV2ItemById.item.id'

Capture the returned item ID, then set Status to Needs triage:

gh api graphql -f query='
  mutation($pid:ID!,$iid:ID!,$fid:ID!,$oid:String!) {
    updateProjectV2ItemFieldValue(input: {
      projectId: $pid,
      itemId: $iid,
      fieldId: $fid,
      value: { singleSelectOptionId: $oid }
    }) { projectV2Item { id } }
  }' \
  -F pid=<project-node-id> \
  -F iid=<item-id> \
  -F fid=<status-field-id> \
  -f oid=<needs-triage-option-id>

The pid / fid / oid values come from <project-config>/project.md; re-fetch them via the introspection query in project-board.md if either mutation returns not found.

5d — Post the status-rollup comment

gh issue comment <new-issue-number> \
  --repo <tracker> \
  --body-file /tmp/import-md-<basename>-<index>-rollup.md

The rollup body is the one drafted in Step 3e with placeholders filled.

5e — Cleanup (per finding)

Delete /tmp/import-md-<basename>-<index>-body.md and /tmp/import-md-<basename>-<index>-rollup.md. They served their purpose for this finding and would otherwise accumulate.

5f — Loop progress

After every finding lands, print a short one-liner so the user can see progress on long batches:

[K/N] <tracker>#NNN — <finding title>

If a single finding's gh api call fails (rate limit, transient network error, schema mismatch), surface the failure with the finding's index and continue with the rest. Do not abort the batch on the first failure — the user can re-invoke for the failed indices once the cause is fixed.

Step 6 — Recap

Print a one-screen recap:

• File imported (<basename>, <N> findings parsed).
• For each kept finding: <tracker>#NNN (clickable), title.
• For each skip-ped finding: index, title, reason if surfaced (possible duplicate, user skip, etc.).
• For each failed finding: index, title, failure cause (so the user can re-invoke).

Then a one-line hand-off:

Next: triage each new tracker per Step 3 of the handling process. Run sync-security-issue on <tracker>#NNN once the validity discussion progresses.

Do not auto-invoke sync-security-issue — these trackers are freshly created in Needs triage and have nothing to sync until the validity discussion produces signal.

What this skill does not do

• Does not run the validity discussion. Every finding lands as Needs triage; Step 3 of the handling process happens in tracker comments after import.
• Does not draft a reporter reply. There is no reporter — the markdown file is the report, and any clarification questions the team has about a finding are recorded as comments on the resulting tracker, not on a Gmail thread.
• Does not allocate CVEs. A finding tagged **Severity:** HIGH in the source markdown is still unassessed from the security team's perspective; the CVE-allocation gate (per allocate-cve) requires the team's own validity decision first.
• Does not parse markdown formats other than the one documented in Step 1. If the input file uses a different shape (e.g. ### Title instead of # Title, or a YAML front-matter block instead of **Field:** lines), surface a one-line ask for the user to either reformat the file or open the trackers manually. The skill must not silently best-effort parse a divergent shape; the resulting trackers would be subtly malformed and confuse the rest of the lifecycle.
• Does not characterise the source as authoritative. The status-rollup line Severity (from source): HIGH (informational; CVSS scoring happens at allocation) is the standard wording — the source's tags are recorded, not adopted.

Failure modes

Examples

Example 1 — A six-finding AI-scan output

import findings from /tmp/scan-michaelwinser-airflow-2026-04-28.md

The skill parses six findings (severities: HIGH×2, MEDIUM×2, LOW×2). The duplicate guard flags one HIGH as a possible duplicate of an already-tracked deserialization finding; the user replies skip 1, accepting the duplicate hint. The remaining five land as <tracker>#NNN..#NNN+4 in Needs triage. Recap shows the five new tracker URLs and one skip with the duplicate reference.

Example 2 — A single-finding scanner export

import findings from ~/Downloads/sast-export.md

The file contains one finding (a SAST report exported as markdown). The skill parses, surfaces a one-row proposal, the user replies go, the tracker lands. The cardinality is the same as a Gmail import; the only difference is the source format.

Example 3 — Malformed input

import findings from /tmp/notes.md

/tmp/notes.md is a free-form scratch file — no **Severity:** lines, no ----separated blocks. Step 0's sanity check fires; the skill stops with the expected-shape ask and does not create any tracker.