who-really-owns-it

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown content providing workflows for corporate intelligence and does not contain any executable scripts, command line tools, or remote code downloads.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and analyzing data from external, untrusted corporate registries.
  • Ingestion points: Data retrieved from third-party sources such as OpenCorporates, Companies House, SEC EDGAR, and various national business registers.
  • Boundary markers: The instructions do not define specific delimiters or guidelines to prevent the agent from following instructions potentially embedded in external registry data.
  • Capability inventory: While the skill itself has no code, it directs the agent to utilize other OSINT tools (e.g., find-anyone, graph-the-network) to process retrieved information.
  • Sanitization: No explicit mention is made of sanitizing or validating external registry content before analysis.
  • Assessment: This represents a standard operational surface for OSINT research tools and is considered safe within the context of its primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 11:54 AM
Security Audit — agent-trust-hub — who-really-owns-it