cw-story-critique

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

• Third-party content exposure detected (high risk: 0.80). The skill's "4. Use Web Search When Helpful" instruction in SKILL.md explicitly directs the agent to fetch and interpret content from the open web (genre examples, similar stories, fact-checking), which is untrusted third‑party content the agent would read as part of its workflow.