modelslab-chat-generation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides integration guides and code snippets for the ModelsLab LLM service. All network communication is restricted to the vendor's official domain (modelslab.com).\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external data by an LLM, creating a potential surface for indirect prompt injection.\n
- Ingestion points: User-provided text strings are accepted through function arguments in SKILL.md.\n
- Boundary markers: Not explicitly defined in the boilerplate code samples.\n
- Capability inventory: The skill uses the requests library and openai SDK to transmit data to the API.\n
- Sanitization: Input is handled as raw strings for API submission.
Audit Metadata