code-stats
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes codebase files through tokei and difft, which creates a surface for indirect prompt injection if the files being analyzed contain malicious instructions designed to influence the agent context.
- Ingestion points: Local files analyzed in SKILL.md, references/difft-advanced.md, and references/tokei-advanced.md.
- Boundary markers: Absent in the provided command examples for delimiting untrusted content.
- Capability inventory: Uses the Bash tool to execute file system analysis and git commands (SKILL.md).
- Sanitization: No explicit sanitization or filtering of file content is performed before the tool output is presented to the agent.
Audit Metadata