changelog-composer

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the repository's git logs and pull request records.
  • Ingestion points: The workflow extracts content from commit messages and PR descriptions using 'git log' and 'gh pr list' commands as specified in Phase 1 of the SKILL.md.
  • Boundary markers: No delimiters or explicit instructions to ignore potentially malicious embedded commands are present in the processing logic.
  • Capability inventory: The skill utilizes the 'git' and 'gh' CLI tools to retrieve project data.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the retrieved content before it is incorporated into the prompt or output.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 06:25 AM