agent-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 3 "Research the Role" in SKILL.md explicitly instructs "IF web search is available and the domain is unfamiliar: use it to verify terminology and frameworks," which requires fetching and interpreting open/public web content to shape the agent's vocabulary, deliverables, and decisions—exposing the agent to untrusted third-party content that could carry indirect prompt injection.