design-critique

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources, creating a potential surface for indirect prompt injection.
  • Ingestion points: The skill fetches HTML/CSS from URLs using WebFetch and analyzes uploaded code files and design documents.
  • Boundary markers: The instructions lack explicit delimiters or 'ignore' commands to isolate the agent from potentially malicious natural language instructions hidden within the ingested design data.
  • Capability inventory: The skill utilizes remote data fetching and static analysis of source code.
  • Sanitization: The skill does not specify any sanitization or filtering of the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:28 PM
Security Audit — agent-trust-hub — design-critique