update-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local environment, including commit logs and file diffs, to generate changelog entries. This could allow malicious content in a project file to influence the agent's behavior.
- Ingestion points: Reads from package.json, CHANGELOG.md, and the output of git log and git diff commands.
- Boundary markers: Implements a strict requirement for user approval before writing any files or creating commits.
- Capability inventory: Possesses the ability to modify local files, execute git commands, and create GitHub releases.
- Sanitization: Recommends the use of DOMPurify for rendering HTML and uses structured JSON/TS templates for data management.
Audit Metadata