changelog-as-war-story
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read, search, and analyze content from project-tracked markdown files (e.g., CLAUDE.md). This creates a potential surface where malicious instructions embedded in documentation could be processed by the agent.
- Ingestion points: The agent is directed to read documentation files specified by the $DOC environment variable and search through all project markdown files using
git grep. - Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between informational documentation content and executable instructions.
- Capability inventory: The skill utilizes shell commands including
grep,git log,git grep, andgit ls-filesto inspect and verify references within the project repository. - Sanitization: The skill does not implement validation or sanitization of the markdown file content before performing search and analysis operations.
Audit Metadata