audit-code-quality

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and analyze untrusted data from the repository's documentation and source code to identify and fix anti-patterns. This creates a surface where malicious instructions embedded in the codebase could influence the agent's behavior during refactoring or command execution.\n
  • Ingestion points: The agent reads CONTRIBUTING.md, .cursor/rules/*.md, and performs repository-wide searches via rg (ripgrep) on source files.\n
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or provide explicit warnings to the agent to ignore instructions embedded within the analyzed code.\n
  • Capability inventory: The agent has the capability to read files (cat, rg), write/modify source code (refactoring fixes), and execute shell commands (e.g., git log, tsc, and scripts defined in package.json).\n
  • Sanitization: Absent. There is no mention of filtering, escaping, or validating the content of repository files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:26 PM