logo-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to run web_search and image_search in Phase 1 ("Research the landscape" in SKILL.md) to fetch competitor logos and public web content which the agent must read, synthesize, and use to drive design decisions and iteration, exposing it to untrusted third‑party content that could carry indirect prompt injection.