changelog-generator
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised of documentation and instructions for the agent to process git commit messages. No suspicious code, obfuscation, or persistence mechanisms were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest and process external git commit history, creating a potential surface for indirect prompt injection if commit messages contain malicious instructions.
- Ingestion points: Git commit history and project files like CHANGELOG_STYLE.md (SKILL.md).
- Boundary markers: Absent; instructions do not specify delimiting commit messages.
- Capability inventory: Text analysis, categorization, and Markdown formatting; no network or file system write capabilities are included in the skill.
- Sanitization: Absent; the agent is expected to translate the content as-is.
Audit Metadata