changelog-maintenance

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for document maintenance and does not engage in network activity or use external scripts.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection. * Ingestion points: Commit messages and pull request descriptions are used as sources in SKILL.md. * Boundary markers: No specific delimiters are used to isolate untrusted data. * Capability inventory: The skill modifies CHANGELOG.md file content. * Sanitization: The process includes a validation step for the generated entries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:00 AM
Security Audit — agent-trust-hub — changelog-maintenance