antimatter-codebase-structure-review
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external codebase data which could contain malicious instructions meant to influence the agent's behavior during the review process.
- Ingestion points: The skill reads file hierarchies, commit ranges, branch diffs, and specific file contents as part of the audit (Phase 0 and Phase 1).
- Boundary markers: The skill lacks explicit instructions to ignore natural language commands that might be found within the analyzed code files or commit messages.
- Capability inventory: The agent likely uses tools for file system access, directory listing, and version control (git) to perform the requested audit.
- Sanitization: There is no evidence of content sanitization or filtering to prevent the execution of instructions embedded in the analyzed code.
Audit Metadata