project-standards-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon the contents of repository files (CLAUDE.md, AGENTS.md, and source code diffs). This creates a vulnerability surface where a malicious actor could embed instructions within these files to influence the agent's behavior during the review process.
- Ingestion points: The skill reads standards files and repository content using the Read, Grep, and Glob tools (SKILL.md).
- Boundary markers: The instructions require the agent to cite specific rules and lines, which provides a logical constraint, though no formal data delimiters are used to separate ingested content from instructions.
- Capability inventory: The agent has access to powerful tools including Bash, Read, Grep, and Glob.
- Sanitization: There is no mention of sanitizing or escaping the content read from external files before processing.
Audit Metadata