web-security

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and inspects content from external targets (e.g., "curl http://target/robots.txt", "curl http://target/.git/HEAD", gobuster/ffuf directory enumeration and sqlmap -u URL) which are untrusted public web resources the agent would read and interpret as part of its workflow.