creativeclaw-find-examples
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to search, retrieve, and process prompt examples from an external catalog for use in media generation workflows. This creates a surface for indirect prompt injection, as the agent is instructed to adapt content from a remote source and pass it to other generation tools. This is a functional requirement of the skill and the risk is mitigated by the instructions requiring the agent to adapt the prompts based on user input rather than executing them blindly.
Audit Metadata