uapi-get-network-wxdomain

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface because it processes untrusted data from an external API source. 1. Ingestion points: Data entering the agent's context via the response from the GET /network/wxdomain API endpoint. 2. Boundary markers: Absent; there are no instructions or delimiters to distinguish external API content from internal agent instructions. 3. Capability inventory: The agent is authorized to perform network requests to uapis.cn and access local reference files. 4. Sanitization: Absent; no validation, filtering, or sanitization rules are defined for the data returned by the diagnostic API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 06:42 AM
Security Audit — agent-trust-hub — uapi-get-network-wxdomain