release-notes
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests untrusted data from repository history, which could contain malicious instructions designed to manipulate the AI's output during release note generation. \n
- Ingestion points: Git commit history (
git log), file differences (git diff), and GitHub CLI PR lists (referenced in SKILL.md). \n - Boundary markers: Absent; the instructions do not include delimiters or warnings to the agent to ignore instructions embedded in the repository metadata. \n
- Capability inventory: Use of
git,rg(ripgrep), andgh(GitHub CLI) to access and search repository content. \n - Sanitization: Absent; the skill summarizes retrieved text directly into the final Markdown output.
Audit Metadata