pick-model
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local source code and configuration files to identify model usage patterns, creating a vulnerability surface where malicious instructions embedded in the code (e.g., in comments) could influence the agent's optimization recommendations.
- Ingestion points: Source code and configuration files are searched for model IDs, SDK calls, and agent definitions (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety markers to prevent the agent from following instructions found within the files it reads.
- Capability inventory: The skill can modify configuration constants or environment variables upon user approval (SKILL.md).
- Sanitization: No sanitization or validation of the file content is performed prior to analysis.
Audit Metadata