clawhunter-content-studio
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves live API specifications and configuration metadata from the vendor's domain (https://clawhunter.fun/llms.txt and https://clawhunter.fun/openapi.json). This allows the agent to maintain current knowledge of available endpoints and their requirements.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
- Ingestion points: Untrusted external data enters the agent's context through the research tool (/api/v1/tools/research) and social media interactions (/api/v1/tools/tweet) as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or isolation techniques for processed external content.
- Capability inventory: The skill possesses the capability to generate social media content and media production prompts (SKILL.md, references/visual.md).
- Sanitization: The skill documentation specifies that generation and research inputs are processed through content moderation on the vendor's servers.
Audit Metadata