content-quality-auditor

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves analyzing web pages, reviews, comments, and third-party exports as evidence (SKILL.md lines 60-62), which allows outsider-authored free text into the agent's ingestion path via arbitrary web pages, search results, or fetched content (low risk because the agent or user must fetch or specify specific URLs/sources).