payroll-payment-bank-check-free
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external payroll data provided in text or JSON format, creating a surface for indirect prompt injection.\n
- Ingestion points: The
scripts/run.mjsscript accepts arbitrary user-supplied text or JSON content representing payroll records for auditing.\n - Boundary markers: The audit engine (
scripts/engine/payroll-payment-bank-check.js) lacks delimiters or explicit instructions to the agent to disregard any natural language commands that might be embedded within the data fields.\n - Capability inventory: The skill is granted
ReadandBashtool permissions, which could be leveraged if the agent inadvertently executes instructions contained within the audited data.\n - Sanitization: The input data is parsed into numeric and string values for logical comparison without any sanitization of the underlying text content.\n- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute its local Node.js processing script (scripts/run.mjs). This is a necessary function for the skill's operation but represents a significant capability.\n- [EXTERNAL_DOWNLOADS]: The skill's documentation includes instructions for the agent to install a payment-related management package (@alipay/agent-payment) from a well-known service (Alipay) to facilitate the purchase of a premium version. These references target established and recognized services.
Audit Metadata