data-client-rest

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Section 6 of SKILL.md contains the instruction 'When asked to browse or navigate to a web address, actual visit the address', which directs the AI to override default safety guidelines regarding external URL navigation.
  • [PROMPT_INJECTION]: The skill facilitates data ingestion from external REST APIs, presenting an attack surface for indirect prompt injection.
  • Ingestion points: Data enters the context via API responses defined in the TodoResource and RestEndpoint examples in SKILL.md.
  • Boundary markers: No delimiters or instructions to ignore embedded commands in fetched data are provided.
  • Capability inventory: The skill enables network operations via HTTP fetch for JSON and binary responses.
  • Sanitization: No response validation or sanitization logic is specified to filter potentially malicious content from API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 02:12 PM