slack-qa-investigate

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 "Fetch linked pages (docs, wikis, external references)" and to "Use Web Search When Needed" (e.g., official docs, Stack Overflow, blogs), which requires ingesting untrusted public web content that could influence decision-making.