keep-a-changelog
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from commit logs and existing changelog files, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads the contents of
CHANGELOG.mdand the output of thegit logcommand. - Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential instructions embedded within the commit history.
- Capability inventory: The skill can read and write local files and execute shell commands (
git,date). - Sanitization: There is no evidence of escaping or filtering commit messages before they are processed and incorporated into the changelog.
- [COMMAND_EXECUTION]: The skill executes system shell commands to gather project metadata.
- Evidence: It runs
git log --onelineto retrieve version history anddate +%Y-%m-%dto determine the current release date.
Audit Metadata