offensive-osint-role

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions direct the agent to adopt an 'Offensive OSINT Operator' persona focused on identifying leaked credentials and facilitating harmful activities such as phishing campaigns and password spraying.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from public records and leaked repositories, which serves as an attack surface for indirect prompt injection.
  • Ingestion points: Public records, exposed Git repositories, and breached password datasets (mentioned in SKILL.md).
  • Boundary markers: No delimiters or specific instructions are provided to ignore embedded commands or adversarial text within the processed data.
  • Capability inventory: Identifying credentials and coordinating handoffs for phishing and password spraying actions.
  • Sanitization: There is no evidence of validation or sanitization of the external content before it enters the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 02:09 PM
Security Audit — agent-trust-hub — offensive-osint-role