update-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and summarize external data from git commit messages and existing changelog files. This represents an indirect prompt injection surface where the agent could potentially encounter and act upon instructions embedded within commit messages written by other contributors.
- Ingestion points: The agent reads commit logs via
git logand project files likeCHANGELOG.mdorCHANGELOG. - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore embedded commands within the processed data.
- Capability inventory: The skill allows for command execution (
git) and file system modifications (updating the changelog file). - Sanitization: There are no instructions provided for filtering or sanitizing the commit messages before they are processed by the agent.
Audit Metadata