changelog-generator
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of markdown documentation and usage examples. There are no scripts, binaries, or configuration files that execute logic or perform network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze git commit history, which constitutes untrusted external data. While this presents an indirect prompt injection surface if a malicious commit contains agent-specific instructions, the skill does not include any scripts or elevated capabilities that would facilitate an exploit. Ingestion points: Git commit history read from the local repository (SKILL.md). Boundary markers: None provided in the skill instructions. Capability inventory: Basic git log reading and writing to local files like CHANGELOG.md. Sanitization: No specific instructions are provided to sanitize or escape commit messages before analysis.
Audit Metadata