unsplash-integration

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for using the Unsplash API and web service to source photography. All identified external references (unsplash.com) are to well-known, legitimate services.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from an external API (Unsplash).
  • Ingestion points: Image metadata and URLs fetched from the Unsplash API during the execution workflow.
  • Boundary markers: None explicitly defined in the instructions for isolating external content.
  • Capability inventory: The skill does not request or use high-risk capabilities such as arbitrary command execution, file system writes, or sensitive data access.
  • Sanitization: No specific sanitization methods are mentioned, but the data is limited to imagery assets for UI/UX purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 01:23 PM
Security Audit — agent-trust-hub — unsplash-integration