multi-banned-words

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with an external domain doubaoya.com to perform text analysis.
  • Evidence: The scripts/check_multi.py script defines API_URL = "https://doubaoya.com/api/apis/tool/check-banned-words/call" and uses urllib.request to send user content to this endpoint.
  • [PROMPT_INJECTION]: The skill contains instructions to pass through a notice field from the API response directly to the user, which could be used to inject instructions or deceptive content from the remote service.
  • Ingestion points: The notice field in the JSON response from doubaoya.com (documented in SKILL.md).
  • Boundary markers: Absent; the skill is instructed to relay the text "as-is".
  • Capability inventory: HTTP POST operations via urllib.request in scripts/check_multi.py.
  • Sanitization: Absent; the instructions specify the field should be transferred without modification.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 11:42 AM
Security Audit — agent-trust-hub — multi-banned-words