competitive-intelligence-spider

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to fetch and scan competitor URLs (see "Step 1: Fetch Current State" and the CLAUDE.md/YAML competitor URL examples) — i.e., it ingests untrusted public web pages and uses their content to drive alerts and drafted responses, which could allow indirect prompt injection.