apply-semantic-versioning
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git history, which represents a potential attack surface if an attacker can commit code to the repository.
- Ingestion points: The skill reads git commit messages using
git login Step 2 to classify change types. - Boundary markers: There are no explicit instructions to the agent to ignore or delimit potentially malicious content within commit messages.
- Capability inventory: The skill utilizes file reading, text searching (
grep), and version control commands (git tag). While it identifies files to update, the environment is restricted to the tools specified in the frontmatter. - Sanitization: No sanitization is performed on the commit messages before they are analyzed for versioning logic.
Audit Metadata