How do I install the Safety/secret Detector skill?

Run npx skillmds@latest add frankxai/safety-secret-detector 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 Safety/secret Detector safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Safety/secret Detector?

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 Safety/secret Detector free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Safety/secret Detector?

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

Safety/secret Detector by frankxai — Agent Skill

Name: Safety/secret Detector
Author: frankxai

Safety/secret Detector

Scan any export, file, or vault batch for credentials, API keys, tokens, and sensitive data before they leave the local machine. Fires automatically on all Claw export operations. Default skill for Starlight Sentinel and Attestation Claw.

frankxai Updated Sep 17, 2026

File contents

Secret Detector

Nothing sensitive exits the local machine without explicit human awareness.

When This Skill Activates

Any content is about to be written outside ~/.starlight/ to an external destination
Any vault export is generated for a platform adapter
Any content is passed to an external MCP server
Keywords: "export", "publish", "send", "upload", "share", "transmit"
Default for: Starlight Sentinel

What This Skill Does

Scans content for credential patterns, personal identifiers, and sensitive data before it leaves the local machine. Blocks export if secrets are found. Never auto-redacts — always surfaces findings to the user for an explicit decision.

Procedures

Procedure 1: Pre-Export Scan

Receive content blob pending export

Run pattern detection against the full content:

Pattern	Example	Action on match
API keys	`sk-...`, `pk_...`, `ghp_...`, `xoxb-...`	BLOCK + report
Private keys	`-----BEGIN PRIVATE KEY-----`	BLOCK + report
Passwords in config	`password=`, `passwd=`, `secret=`	BLOCK + report
Email addresses	`user@domain.com` in unexpected context	WARN + report
Phone numbers	`+1-555-...`, formatted phone patterns	WARN + report
Credit card patterns	16-digit sequences with separators	BLOCK + report
Government IDs	SSN patterns, national ID formats	BLOCK + report

If BLOCK patterns found: halt export, generate SECRET_SCAN_REPORT.md, present to user
If WARN patterns found: present to user with option to proceed or redact
If clean: return APPROVED for export

Procedure 2: Scan Report Generation

Create /security/SECRET_SCAN_REPORT.md
Include: content source, patterns detected, line references (not the secrets themselves)
Present options: [redact and retry] / [cancel export] / [I confirm this is safe, proceed]
Log the decision with user action

Procedure 3: False Positive Handling

User declares a detected pattern is not sensitive
Record the declaration with timestamp + user confirmation
Add to local allowlist for this session (not persisted globally)
Proceed with export

Integration Points

Vaults: No vault access needed — operates purely on content in transit
Agents: Starlight Sentinel
Skills: Composes with private-public-split for structural classification; permission-gate for the approval flow
Claws: Called by every Claw that generates exports (Memory, Creator, Attestation, Reclamation)

Quality Criteria

Zero false negatives on common credential patterns
False positives surface clearly as warnings, not blocks (where safe)
User is always in control — no silent redaction or silent pass
Scan report is human-readable, not a raw regex dump

---name: safety-secret-detectordescription: Scan any export, file, or vault batch for credentials, API keys, tokens, and sensitive data before they leave the local machine. Fires automatically on all Claw export operations. Default skill for Starlight Sentinel and Attestation Claw.---# Secret Detector> Nothing sensitive exits the local machine without explicit human awareness.## When This Skill Activates- Any content is about to be written outside `~/.starlight/` to an external destination- Any vault export is generated for a platform adapter- Any content is passed to an external MCP server- Keywords: "export", "publish", "send", "upload", "share", "transmit"- Default for: Starlight Sentinel## What This Skill DoesScans content for credential patterns, personal identifiers, and sensitive data before it leaves the local machine. Blocks export if secrets are found. Never auto-redacts — always surfaces findings to the user for an explicit decision.## Procedures### Procedure 1: Pre-Export Scan1. Receive content blob pending export2. Run pattern detection against the full content: | Pattern | Example | Action on match | |---------|---------|----------------| | API keys | `sk-...`, `pk_...`, `ghp_...`, `xoxb-...` | BLOCK + report | | Private keys | `-----BEGIN PRIVATE KEY-----` | BLOCK + report | | Passwords in config | `password=`, `passwd=`, `secret=` | BLOCK + report | | Email addresses | `user@domain.com` in unexpected context | WARN + report | | Phone numbers | `+1-555-...`, formatted phone patterns | WARN + report | | Credit card patterns | 16-digit sequences with separators | BLOCK + report | | Government IDs | SSN patterns, national ID formats | BLOCK + report |3. If BLOCK patterns found: halt export, generate SECRET_SCAN_REPORT.md, present to user4. If WARN patterns found: present to user with option to proceed or redact5. If clean: return APPROVED for export### Procedure 2: Scan Report Generation1. Create `/security/SECRET_SCAN_REPORT.md`2. Include: content source, patterns detected, line references (not the secrets themselves)3. Present options: [redact and retry] / [cancel export] / [I confirm this is safe, proceed]4. Log the decision with user action### Procedure 3: False Positive Handling1. User declares a detected pattern is not sensitive2. Record the declaration with timestamp + user confirmation3. Add to local allowlist for this session (not persisted globally)4. Proceed with export## Integration Points- **Vaults:** No vault access needed — operates purely on content in transit- **Agents:** Starlight Sentinel- **Skills:** Composes with `private-public-split` for structural classification; `permission-gate` for the approval flow- **Claws:** Called by every Claw that generates exports (Memory, Creator, Attestation, Reclamation)## Quality Criteria- Zero false negatives on common credential patterns- False positives surface clearly as warnings, not blocks (where safe)- User is always in control — no silent redaction or silent pass- Scan report is human-readable, not a raw regex dump

Frequently asked questions