skills/okou-ai/okou-skills/finicity/Gen Agent Trust Hub

finicity

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the okou CLI and jq to interface with banking services. These commands are used to list accounts, balances, and transactions in a read-only manner. The okou tool is a vendor-provided resource, and the use of jq is a standard practice for processing structured data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes financial transaction data retrieved from external banking providers, which could contain untrusted content.
  • Ingestion points: Transaction details and memos retrieved via the okou banking transactions command (SKILL.md).
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat data within transaction fields as non-instructional content.
  • Capability inventory: The skill possesses the ability to execute shell commands (okou, jq) to interact with the environment.
  • Sanitization: The skill uses jq to select specific JSON fields, providing structural validation, but does not perform content-level sanitization of strings within the transaction data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:06 PM
Security Audit — agent-trust-hub — finicity