company-enrichment

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes firmographic and B2B intelligence data from external sources (Apollo, Strale, Akta), which represents a surface for indirect prompt injection.
  • Ingestion points: Untrusted external data is ingested through the sandbase_call_tool referencing multiple third-party intelligence providers in SKILL.md.
  • Boundary markers: The skill lacks explicit instructions to use delimiters or to disregard potentially malicious instructions embedded within the enriched data results.
  • Capability inventory: The available capabilities are limited to tool description and execution (sandbase_describe_tool, sandbase_call_tool), which are used for read-only research purposes.
  • Sanitization: There are no specified sanitization or filtering protocols for the data retrieved from external platforms.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:31 PM
Security Audit — agent-trust-hub — company-enrichment