claudish-usage

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs agents to run Claudish against external/third‑party models and endpoints (e.g., OpenRouter/Gemini/OpenAI via claudish --models, claudish --json, custom http://... endpoints and user-provided model IDs) and explicitly reads/parses the produced result files (e.g., /tmp/claudish-result-*.md) and JSON outputs, meaning the agent ingests and interprets untrusted third‑party model outputs as part of its workflow.