security
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands to initialize Husky (
npx husky init) and run GitLeaks (gitleaks protect,gitleaks detect). - [EXTERNAL_DOWNLOADS]: Uses
npxto fetch thehuskyinitialization script from the npm registry. - [PERSISTENCE]: Configures a pre-commit hook in
.husky/pre-commit. This ensures the GitLeaks security check runs automatically on every commit. - [INDIRECT_PROMPT_INJECTION]: The skill invokes a
security-auditorsubagent to analyze the project's source code, creating a surface for indirect prompt injection. - Ingestion points: The
security-auditortask processes the local codebase as input. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the subagent task.
- Capability inventory: The skill possesses capabilities for shell command execution (
Bash), file system modification (Write,Edit), and reading files (Read,Glob,Grep). - Sanitization: There is no evidence of sanitization or filtering of the codebase content before it is processed by the agent.
Audit Metadata