clawhunter-content-studio

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes POST /api/v1/tools/research, which performs a live search of the web and X and ingests the resulting page/post text (outsider-authored free text) into the agent’s LLM context along with cited sources.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching the live spec at https://clawhunter.fun/llms.txt (and/or https://clawhunter.fun/openapi.json) at runtime and treats that file as the authoritative source of endpoints, parameters, prices and enums that directly determine which endpoints/parameters/prompts the agent uses, so this is a runtime external dependency that controls agent behavior.