code-simplifier
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from analyzed code and the repository configuration, creating a surface for indirect prompt injection.\n
- Ingestion points: repository files, git diff output, and the AGENTS.md file (SKILL.md).\n
- Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore embedded directives in analyzed code.\n
- Capability inventory: The agent performs file system reads and executes git commands.\n
- Sanitization: No sanitization is performed on ingested code or configuration files.\n- [EXTERNAL_DOWNLOADS]: The skill links to the official Claude plugins repository on GitHub for its design origin.\n
- Evidence: README.md references github.com/anthropics/claude-plugins-official.
Audit Metadata