finta-webhooks-events

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a Python script designed to process external CSV exports (‘export_path’). This creates an ingestion point for untrusted data that could contain malicious instructions aimed at influencing the agent's behavior.
  • Ingestion points: ‘SKILL.md’ (via the ‘get_followup_reminders’ Python function).
  • Boundary markers: No delimiters or safety instructions are defined to separate processed data from agent instructions.
  • Capability inventory: The skill is configured with ‘Read’, ‘Write’, and ‘Edit’ tools, and the script performs file read operations using ‘pandas’.
  • Sanitization: The provided script template lacks validation or sanitization for the content of the CSV file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:47 AM
Security Audit — agent-trust-hub — finta-webhooks-events