Skills
skills/caomeiyouren/momei/code-quality-auditor/Gen Agent Trust Hub

code-quality-auditor

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using pnpm (e.g., pnpm lint, pnpm typecheck, pnpm test, pnpm ai:check) to validate code changes as described in SKILL.md and references/validation-matrix.md.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted data from git changes. Ingestion points: The agent reads git diff and staged changes to establish review context (SKILL.md). Boundary markers: No specific delimiters or instructions are provided to ensure the agent ignores instructions embedded within the diff content. Capability inventory: The agent has the authority to run shell commands (pnpm) and perform file system writes (to artifacts/review-gate/). Sanitization: There is no process for validating or escaping content ingested from git diffs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 11:35 AM