companies-house-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the scavio library for both Python and Node.js environments. These are identified as official SDKs belonging to the skill's authoring vendor (scavio-ai).
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from an external API source (the Companies House register via Scavio API), which creates an indirect prompt injection surface. The risk is considered low as the ingestion is central to the skill's stated purpose.
  • Ingestion points: The skill instructions in SKILL.md describe processing JSON data from /search, /company, /officers, and /filing-history endpoints.
  • Boundary markers: The instructions do not define specific boundary markers or delimiters for the external registry content.
  • Capability inventory: The skill uses network operations to communicate with api.scavio.dev using the requests library and scavio SDK as documented in SKILL.md.
  • Sanitization: No explicit sanitization of the external registry data is performed before it is handled by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:24 PM
Security Audit — agent-trust-hub — companies-house-api