How do I install the Review Security skill?

Run npx get-skill add gtrabanco/review-security in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Review Security safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Security?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Security free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Review Security?

gtrabanco (@gtrabanco) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Security by gtrabanco — Agent Skill

Name: Review Security
Author: gtrabanco

Review Security

Internal security review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks secrets, input validation, injection, authn/authz, PII exposure, and dependency risk on the changed surface. Findings only; never edits code.

gtrabanco Updated Nov 11, 2026

File contents

Review Security (internal)

Composed by review-change / product-audit within their conversation — on any agent, follow this file inline as the routed step. Findings only; never edits, never refactors.

Scope

The caller's diff or path/glob — the shape is the finder contract's (skills/review-implementation/references/FINDER_CONTRACT.md, this section's owner). State the scope at the top of the returned table.

Checklist (evaluate EVERY item — none is optional; n/a must be stated)

✓ No secrets/credentials/tokens in code, config, tests, or fixtures (grep the diff for key-like strings) ✓ Every external input on the changed paths is validated/sanitized before use ✓ No injection vectors (SQL/command/path/template) — parameterized/escaped, never concatenated ✓ AuthN/AuthZ enforced on every new/changed endpoint or entry point (cite where) ✓ No PII or secrets written to logs/error messages on the changed paths ✓ Webhooks/callbacks verify signatures before processing ✓ Rate limiting / abuse controls considered where a new public surface appears (n/a if none) ✓ New/updated dependencies pinned and free of known-critical advisories — run bun scripts/dependency-advisory-pass.mjs (node fallback if bun is not installed) and cite the row it prints for a dependency this change adds or updates: a blocking row is a finding, a report-only row is a report-note, and a pre-existing advisory on an untouched dependency is never a finding here — the baseline-advisory rule, owner review-implementation (CLASSIFY.md §Severity ladder) ✓ Error responses don't leak stack traces or internal paths ✓ Unsafe deserialization / dynamic evaluation of untrusted data absent

Materiality bar

The bar is owned by skills/review-implementation/references/FINDER_CONTRACT.md — apply it as written: cite the rule it violates beside the evidence; never pad the table.

Return exactly

Sev and Impact are the two published closed sets (BLOCKER | CRITICAL | WARNING | SUGGESTION and blocking | docs-only | report-only); their meanings are owned by review-implementation (CLASSIFY.md §Severity ladder) — assign a token, never a prose grade.

REVIEW SECURITY — scope: <scope>

| # | Finding | Sev | Impact | Evidence | Suggested fix |
|---|---------|-----|--------|----------|---------------|
| 1 | <what>  | BLOCKER|CRITICAL|WARNING|SUGGESTION | blocking|docs-only|report-only | <file:line> | <smallest action> |

Checklist: <n> evaluated, <n> pass, <n> findings, <n> n/a (<which + why>)
Summary: <1-2 sentences>
Decision: PASS | FAIL

FAIL if any BLOCKER, CRITICAL or WARNING finding is open; PASS otherwise. SUGGESTION findings never block — they route to the caller's triage step.

Done when

Every checklist item was evaluated with evidence (file:line or command output) or explicitly marked n/a with the reason.
The fixed-format block above is returned — nothing more, nothing less — and no code was changed.

---name: review-securityuser-invocable: falseversion: 4.10.0author: "Gabriel Trabanco <1969593+gtrabanco@users.noreply.github.com>"license: MITdescription: > Internal security review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks secrets, input validation, injection, authn/authz, PII exposure, and dependency risk on the changed surface. Findings only; never edits code.metadata: source: https://skillmd.com/skills/gtrabanco/review-security---# Review Security (internal)Composed by `review-change` / `product-audit` within their conversation — on anyagent, follow this file inline as the routed step. **Findings only; never edits,never refactors.**## ScopeThe caller's diff or path/glob — the shape is the finder contract's(`skills/review-implementation/references/FINDER_CONTRACT.md`, this section's owner). State the scope at the top of thereturned table.## Checklist (evaluate EVERY item — none is optional; n/a must be stated)✓ No secrets/credentials/tokens in code, config, tests, or fixtures (grep the diff for key-like strings)✓ Every external input on the changed paths is validated/sanitized before use✓ No injection vectors (SQL/command/path/template) — parameterized/escaped, never concatenated✓ AuthN/AuthZ enforced on every new/changed endpoint or entry point (cite where)✓ No PII or secrets written to logs/error messages on the changed paths✓ Webhooks/callbacks verify signatures before processing✓ Rate limiting / abuse controls considered where a new public surface appears (n/a if none)✓ New/updated dependencies pinned and free of known-critical advisories — run `bun scripts/dependency-advisory-pass.mjs` (node fallback if bun is not installed) and cite the row it prints for a dependency this change **adds or updates**: a `blocking` row is a finding, a `report-only` row is a report-note, and a pre-existing advisory on an untouched dependency is never a finding here — the baseline-advisory rule, owner `review-implementation` (`CLASSIFY.md` §Severity ladder)✓ Error responses don't leak stack traces or internal paths✓ Unsafe deserialization / dynamic evaluation of untrusted data absent## Materiality barThe bar is owned by `skills/review-implementation/references/FINDER_CONTRACT.md` —apply it as written: cite the rule it violates beside the evidence; never pad the table.## Return exactly`Sev` and `Impact` are the two published closed sets (`BLOCKER | CRITICAL |WARNING | SUGGESTION` and `blocking | docs-only | report-only`); their meaningsare owned by `review-implementation` (`CLASSIFY.md` §Severity ladder) — assign atoken, never a prose grade.```REVIEW SECURITY — scope: <scope>| # | Finding | Sev | Impact | Evidence | Suggested fix ||---|---------|-----|--------|----------|---------------|| 1 | <what> | BLOCKER|CRITICAL|WARNING|SUGGESTION | blocking|docs-only|report-only | <file:line> | <smallest action> |Checklist: <n> evaluated, <n> pass, <n> findings, <n> n/a (<which + why>)Summary: <1-2 sentences>Decision: PASS | FAIL```FAIL if any `BLOCKER`, `CRITICAL` or `WARNING` finding is open; PASS otherwise.`SUGGESTION` findings never block — they route to the caller's triage step.## Done when- Every checklist item was evaluated with evidence (file:line or command output) or explicitly marked n/a with the reason.- The fixed-format block above is returned — nothing more, nothing less — and no code was changed.

Frequently asked questions