extract
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves analyzing source code, which introduces a potential surface for indirect prompt injection if the analyzed files contain malicious instructions. * Ingestion points: Source code and shared UI directories specified by the user or identified via search (SKILL.md). * Boundary markers: Not explicitly defined in the instructions. * Capability inventory: File system searching, reading, and modification for refactoring purposes. * Sanitization: No explicit sanitization of content extracted from source files is mentioned.
Audit Metadata