create-changeset
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted data from the repository's git history.
- Ingestion points: Steps 1, 2, and 3 involve reading git commit logs and diffs using
git logandgit diffto determine versioning logic. - Boundary markers: Absent. The skill instructions do not specify any delimiters or warnings to ignore instructions that might be embedded within commit messages.
- Capability inventory: The skill has access to
Bash(git:*),Bash(pnpm:*),Read, andWritetools, allowing it to modify the filesystem and commit changes. - Sanitization: Absent. There is no mechanism to filter or sanitize the content of commit messages before the agent interprets them to decide between 'major', 'minor', or 'patch' version bumps.
Audit Metadata