social-captions

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These are third‑party GitHub repositories (unknown account) that the README instructs you to clone/install — unvetted code repos can contain malicious scripts, so they should be treated as suspicious until audited.

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

• Third-party content exposure detected (medium risk: 0.30). In the /social-captions workflow, Step 1 explicitly “Read/view whatever the user sent” (including competitor post text or screenshot descriptions) and then Step 1 analyzes it to generate outputs, meaning outsider-authored free text is ingested directly from the user-provided prompt/material.