lint-suite
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code to identify and fix formatting issues, which represents an ingestion of untrusted data. While no malicious intent is evident, the lack of explicit boundary markers or sanitization for file contents creates a potential surface for indirect prompt injection. 1. Ingestion points: Codebase files analyzed during linting (SKILL.md Step 1). 2. Boundary markers: None present. 3. Capability inventory: Command execution for linters, file-write for applying fixes, and git operations for staging changes. 4. Sanitization: None defined; the skill relies on the agent's base safety protocols.
Audit Metadata