changelog-updater
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides specific shell command templates (e.g., git log, git diff, git tag) for the agent to execute. These commands are used to programmatically retrieve the commit history and file changes needed to generate the changelog content.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes data from the repository that an attacker could control. \n
- Ingestion points: Content is read from README.md, CHANGELOG.md, and the output of git log (which includes commit messages). \n
- Boundary markers: The instructions do not define clear delimiters or provide 'ignore' directives for the data being analyzed. \n
- Capability inventory: The skill performs file reads and executes shell commands via subprocesses. \n
- Sanitization: There is no evidence of sanitization or escaping of the ingested text before it is processed by the agent.
Audit Metadata