changelog-generator
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data in the form of git commit messages to generate human-readable changelogs. If a commit message contains malicious instructions, the agent might inadvertently follow them during the summarization process.
- Ingestion points: Commit messages retrieved from the local repository using
git logcommands specified inSKILL.md. - Boundary markers: Absent. The instructions do not explicitly tell the agent to ignore or delimit instructions found within the commit text.
- Capability inventory: The skill utilizes shell commands (
git log) and suggests writing the resulting content to the filesystem (CHANGELOG.md). - Sanitization: Absent. There is no mention of filtering, escaping, or validating the content of the commit messages before they are processed by the LLM.
Audit Metadata