add-model
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data and interpolates it into shell commands, creating a potential injection surface. * Ingestion points: User-provided values for LITELLM_BASE_URL, LITELLM_API_KEY, public model names, and provider credentials defined in the 'Setup' and 'Ask the user' sections of SKILL.md. * Boundary markers: Absent. The instructions do not provide delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the user-supplied configuration values. * Capability inventory: Uses the 'Bash(curl)' tool to execute network requests with the interpolated data. * Sanitization: Absent. There are no instructions for the agent to escape shell metacharacters or validate the format of the user input before executing the curl command.
- [SAFE]: The skill references official documentation hosted on Vercel's platform (litellm.vercel.app), which is a well-known service.
Audit Metadata