changelog-generator
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill files consist solely of Markdown documentation and JSON metadata. There are no executable scripts, binaries, or other active code components.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process git commit history, which is an external data source. This creates a surface for indirect prompt injection if commit messages contain malicious instructions. 1. Ingestion points: Git commit history (SKILL.md). 2. Boundary markers: None specified in instructions. 3. Capability inventory: Text transformation and formatting (no file system or network capabilities in skill). 4. Sanitization: None specified.
- [SAFE]: No malicious patterns, such as prompt injection, credential theft, or unauthorized network access, were found in the skill documentation.
Audit Metadata