storyclaw-autoposter

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the user to paste their StoryClaw API key into chat and contains examples and API/cURL payloads that embed that key verbatim (e.g., "storyclaw_api_key": "" and -F "storyclaw_api_key="), forcing the LLM to handle and output the secret directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the StoryClaw API (POST https://aipuejhjwmabtobjrqdz.supabase.co/functions/v1/storyclaw-api) to fetch and display social media posts, post details, and analytics from user-generated/public platforms via actions like get_posts and get_post, and the agent is expected to read and act on that untrusted third‑party content (including decisions like delete_post), which enables indirect prompt injection risk.