offensive-osint-role

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly directs the agent to collect "breached passwords" and pass them to other roles (e.g., for password spraying), which requires outputting sensitive secret values verbatim and thus creates a direct exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document explicitly instructs harvesting and sharing breached credentials and coordinating password spraying and phishing, which directly facilitates credential theft and offensive attacks.

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

• Third-party content exposure detected (high risk: 0.70). The skill is an OSINT role that studies public records (e.g., exposed Git repos/breached passwords), which implies it may fetch and ingest outsider-authored free text from public web sources at runtime into the agent’s LLM context.