insecure-design
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, exfiltration, or unauthorized command execution were detected. The skill uses standard security tools like semgrep for local analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code as its primary function. Ingestion points include scoped files resolved in Workflow Step 1. While this is an attack surface, the risk is inherent to the primary skill purpose. Boundary markers are absent. Capability inventory includes local tool execution (semgrep) and file reading. No explicit sanitization of input code is defined.
Audit Metadata