payabli-send-payments

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from a local file (payabli-integration.md) at the repository root to configure its behavior and scope.
  • Ingestion points: payabli-integration.md (read on load)
  • Boundary markers: The skill instructs the agent to honor specific headers like ## SDK and ## Pay Out, but does not specify delimiters or instructions to isolate these instructions from potentially malicious data in the rest of the file.
  • Capability inventory: The skill facilitates high-value financial operations, including authorizing payouts (POST /MoneyOut/authorize), creating bills, and generating payment links.
  • Sanitization: No explicit sanitization or filtering logic is provided for the content of the integration file.
  • [EXTERNAL_DOWNLOADS]: The skill references several documentation resources on the official Payabli domain for developer guidance.
  • Evidence: Links to docs.payabli.com for implementation guides regarding managed payables, ghost cards, and Positive Pay.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:23 PM