code-quality-principles

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use common shell utilities to gather code metrics for quality verification.
  • Evidence: Verification steps include executing wc -l <file> to check line counts and rg -c "class " <file> or grep to count class definitions.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided source code, which serves as a potential vector for indirect instructions.
  • Ingestion points: External code files analyzed by the agent as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions within the reviewed code.
  • Capability inventory: The skill only suggests read-only metadata extraction using basic tools (wc, rg, grep). It does not request network access or write operations.
  • Sanitization: No explicit sanitization or filtering of the code content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 10:05 AM
Security Audit — agent-trust-hub — code-quality-principles