govisit-get-place-section

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from a remote API, creating a potential surface for indirect prompt injection if the returned data contains instructions.
  • Ingestion points: Data is fetched from the GoVisit API endpoint at govisit.ai.
  • Boundary markers: The skill includes an explicit instruction for the agent to treat tool output as untrusted data rather than instructions.
  • Capability inventory: The skill is restricted to standard HTTPS communications and has no access to privileged system commands or local files.
  • Sanitization: Input and output data are governed by a strictly defined JSON schema in the contract reference file.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 05:07 PM