dig-through-data-brokers

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues were detected in the skill instructions or referenced files. The content is purely informational and focuses on investigative workflows.
  • [NO_CODE]: The skill contains no executable scripts, configuration files for tool execution, or dynamic context commands. It is restricted to markdown documentation.
  • [PROMPT_INJECTION]: The skill documents a workflow that involves the agent ingesting and processing data from untrusted external sources (third-party data brokers and public record aggregators).
  • Ingestion points: External people-search aggregators (e.g., Spokeo, BeenVerified) and government record portals (e.g., PACER, land registries) as described in the source catalogue.
  • Boundary markers: The skill emphasizes manual verification against primary sources but does not define technical delimiters to prevent the agent from following embedded instructions in external data.
  • Capability inventory: The methodology references the use of other tools for reverse phone lookups, email analysis, and company research.
  • Sanitization: No data sanitization or escaping procedures are described for handling the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 01:24 PM
Security Audit — agent-trust-hub — dig-through-data-brokers