exp-mock-usage-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because its core workflow relies on processing untrusted external data.
- Ingestion points: The Workflow (Step 1) requires the agent to read all provided test and production code files to perform its audit.
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions that might be embedded in code comments or string literals within the analyzed files.
- Capability inventory: No scripts, subprocess calls, or network operations were identified within the skill files; the primary capability is the agent's analytical reasoning and reporting based on the provided code.
- Sanitization: The instructions do not specify any validation or sanitization of the input code files before the agent processes them.
Audit Metadata