recon-sector

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content is an explicitly offensive reconnaissance toolkit: it probes for credential-exposing CORS, mines debug logs for PII/credentials, enumerates XMLRPC and source-leak endpoints, and references exploitation follow-ups — indicating clear intent to harvest sensitive data and identify exploitable services.

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

• Third-party content exposure detected (medium risk: 0.30). Skill.md’s required workflow reads outsider-authored free text from the user-supplied targets file ($TARGETS_FILE), iterating over its lines at multiple runtime steps (e.g., Step 2/3/4/5/6) and using those values as input for subsequent HTTP requests and log/response processing.