recon

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow runs runtime commands like curl to fetch certificate-transparency results (https://crt.sh/...) and uses search-engine dorking/Wayback/public repo discovery, which ingests outsider-authored free text (public web content) into the agent context via command outputs.