osint-recon

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 gather and interpret content from public, user-generated sources (e.g., querying crt.sh via curl and parsing results, Wayback Machine, Pastebin, LinkedIn, GitHub, Shodan, VirusTotal, public S3/GCS buckets), so the agent would fetch and act on untrusted third-party content as part of its workflow.