content-performance-reporter

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests CSV exports from third‑party social platforms uploaded to the Cowork workspace (see "Input: One or more CSV files from analytics platforms..." and Step 1 "Locate Files" in SKILL.md) and requires the agent to read and interpret post titles/metrics to generate recommendations, so untrusted user‑generated content from social media could materially influence its actions.