username-profiling

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documentation follows security best practices for OSINT investigations, including detailed guidance on investigator anonymity, data minimization, and legal authorization.
  • [EXTERNAL_DOWNLOADS]: Instructions involve installing well-known security tools from official package managers and downloading data files from verified GitHub repositories (soxoj, webbreacher).
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface through the ingestion of untrusted data from thousands of external websites (Ingestion points). However, the tools used utilize pattern-based extraction to generate structured reports, which functions as a form of content sanitization (Sanitization). The skill's actions are restricted to local environment CLI execution and report generation (Capability inventory), with no identified instructions to the agent to override safety guardrails (Boundary markers).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:36 PM