nhs-health-content

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a set of high-level safety and editorial principles for processing health information. It includes explicit instructions to preserve clinical uncertainty, avoid diagnostic claims, and require human clinical review.\n- [SAFE]: All external links point to official NHS England service manual domains for reference and provenance purposes.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied health content for auditing and rewriting. While this represents a data ingestion surface, the skill does not possess any capabilities for command execution, file system modification, or network requests, and it includes explicit instructions to maintain clinical safety-netting and boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 09:41 PM
Security Audit — agent-trust-hub — nhs-health-content