osint-methods
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is a documentation-only resource providing methodologies and templates. It contains no executable scripts, shell commands, or automation code.
- [PROMPT_INJECTION]: The skill defines a framework for gathering data from untrusted external sources like social media, web snapshots, and leaked documents. This creates an inherent surface for indirect prompt injection where malicious instructions embedded in the analyzed data could attempt to influence the agent. 1. Ingestion points: Public records, social media (LinkedIn, Twitter), websites, and leaked documents as specified in the OSINT Sources section. 2. Boundary markers: None present in the documentation. 3. Capability inventory: No active capabilities (subprocess, network, file-write) are included in this specific skill. 4. Sanitization: The methodology emphasizes manual verification and anonymization but lacks technical sanitization for data processed by an AI agent.
- [SAFE]: References to external resources (Bellingcat, OSINT Framework) and vendor-owned repositories (Hack23/ISMS-PUBLIC) are for informational purposes and do not involve automated execution or risky downloads.
Audit Metadata