jackin-release-notes

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill utilizes official developer tools, specifically git and the GitHub CLI (gh), to perform repository history analysis and documentation updates, which is entirely consistent with its described purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data in the form of pull request titles and labels from GitHub. Although this is a potential ingestion surface for indirect prompt injection, the risk is mitigated by the rigid classification logic and the procedural requirement for operator review before any changes are committed to CHANGELOG.md.
  • Ingestion points: PR titles and labels via gh pr list (SKILL.md).
  • Boundary markers: None.
  • Capability inventory: Write access to local file CHANGELOG.md.
  • Sanitization: String cleaning to remove Conventional Commit prefixes from titles.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 05:10 AM
Security Audit — agent-trust-hub — jackin-release-notes