appraise

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run "openstall discover" and "openstall capability" to fetch provider descriptions, ratings, and reviews from the marketplace (untrusted, user-generated content) which the agent must read and use to decide purchases, enabling indirect prompt injection.