accounts-payable-agent

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'agenticbtc-mcp' package from the npm registry to perform its core payment routing functions.\n- [COMMAND_EXECUTION]: The configuration instructions utilize 'npx -y agenticbtc-mcp' to execute the MCP server as a subprocess for payment operations.\n- [PROMPT_INJECTION]: The agent is designed to receive and act on data provided by other agents, creating a surface for indirect prompt injection.\n
  • Ingestion points: Payment requests containing amount, recipient, and reference data enter the agent context from the Contracts Agent, Project Manager Agent, or HR Agent.\n
  • Boundary markers: The skill prompt does not provide explicit markers or instructions to isolate external payment request data from the agent's core safety and operational rules.\n
  • Capability inventory: The agent possesses the high-privilege capability to execute real financial transactions via 'agenticbtc.sendPayment'.\n
  • Sanitization: While the agent performs a vendor registry check, it does not implement explicit sanitization or validation of the input strings provided by external requesting agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:44 AM
Security Audit — agent-trust-hub — accounts-payable-agent