run-models
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external AI models and webhooks, which constitutes an attack surface for indirect prompt injection if the external content contains instructions meant to override the agent.
- Ingestion points: Model outputs (text or file URLs) and webhook notification payloads described in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or specific system instructions to ignore content within model outputs.
- Capability inventory: The agent has capabilities to make network requests (POST /v1/predictions, GET /v1/webhooks/default/secret).
- Sanitization: The guidelines recommend validating input parameters against schemas, but do not explicitly detail sanitization of model outputs before further processing.
Audit Metadata