delete-model
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface through the retrieval of external data.
- Ingestion points: Model information is fetched from the LiteLLM proxy's
/model/infoendpoint in SKILL.md. - Boundary markers: There are no isolation markers or specific instructions to the agent to treat the API response as untrusted content.
- Capability inventory: The skill possesses the ability to execute network requests and administrative commands via
Bash(curl:*). - Sanitization: The inline Python script used for parsing extracts and displays raw strings from the JSON response without validation or escaping.
Audit Metadata