payabli-boarding

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to automatically read the payabli-integration.md file from the repository root when the skill is loaded. This behavior creates an attack surface where malicious instructions placed in this file could potentially manipulate the agent's logic or data handling.
  • Ingestion points: The skill reads payabli-integration.md on load and retrieves data from Payabli API responses (such as document requirements).
  • Boundary markers: Absent. The skill does not provide instructions to treat the contents of the integration file as untrusted or delimited data.
  • Capability inventory: The skill has the capability to perform authenticated API requests to create, search, and modify records for businesses, people, and bank accounts, as well as upload documents.
  • Sanitization: Absent. No validation or filtering is specified for the configuration data read from the local file.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 05:07 PM