paid-ad-copy-adapter

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

• Third-party content exposure detected (high risk: 0.80). The skill's required input and workflow explicitly instruct the agent to read and analyze "Original creator content" (the required input #1 and "Step 1: Analyze the Original Content" in SKILL.md), which is untrusted user-generated content (creator captions/scripts) that the agent ingests and uses to drive decisions and generate ad copy, so it could carry indirect prompt-injection instructions.