codeguard-typescript
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes npx eslint for linting and formatting. It uses the --no-install flag for initial checks, which prevents the execution of unverified remote packages.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project files and configurations, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Source files (.ts, .js, etc.) and configuration files (package.json, eslint.config.js).\n
- Boundary markers: None specified for the ingested file content.\n
- Capability inventory: Shell command execution via npx for linting and fixing.\n
- Sanitization: No specific sanitization or escaping of file content is mentioned before the agent processes it for diagnosis.
Audit Metadata