enforce-rules-format
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes the
npx vigilescommand suite to perform compilation, discovery, and checking of rule formats within the local project environment. - [INDIRECT_PROMPT_INJECTION]: The skill reads and interprets instructions from various local project files which could contain untrusted data.
- Ingestion points: Processes content from
CLAUDE.md,AGENTS.md,.cursorrules, and TypeScript specification files (*.spec.ts). - Boundary markers: No explicit delimiters or system warnings are used when processing the contents of these files.
- Capability inventory: Can execute shell commands via
npxand propose modifications to project files. - Sanitization: Implements a human-in-the-loop safety check by explicitly instructing the agent to 'Ask the user before making changes'.
Audit Metadata