brooks-lint

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The workflow documentation suggests executing 'npx antigravity-awesome-skills --claude', which downloads and runs code from a third-party package on the NPM registry.
  • [COMMAND_EXECUTION]: The skill provides shell commands for installing and invoking external tools via 'npx'.
  • [PROMPT_INJECTION]: The skill's primary function is to read and analyze source code files, which constitutes an indirect prompt injection surface.
  • Ingestion points: Reads files like 'PaymentService.ts' for review.
  • Boundary markers: None; the instructions do not explicitly require the agent to ignore instructions embedded within the code being analyzed.
  • Capability inventory: Accesses development tools including 'claude-code' and 'cursor'.
  • Sanitization: No input validation or escaping of reviewed content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 05:13 PM
Security Audit — agent-trust-hub — brooks-lint