accrual-expense-check-free

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation in SKILL.md provides instructions for the agent to install the @alipay/agent-payment package. This package is managed by a well-known financial services organization.
  • [REMOTE_CODE_EXECUTION]: The documentation includes a block of text intended for the AI assistant to execute npx -y @alipay/agent-payment@latest install. This command initiates a remote package installation and execution, which is a standard procedure for installing the payment dependency required for the full version of the tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied ledger data which represents a potential injection surface.
  • Ingestion points: The payload.text variable is ingested and parsed in scripts/engine/accrual-expense-check.js.
  • Boundary markers: The skill does not use specific delimiters or instructions to ignore embedded commands within the ingested ledger text.
  • Capability inventory: The skill frontmatter allows the Bash tool, although the scripts themselves do not programmatically invoke it with user data.
  • Sanitization: There is no specific sanitization or escaping of the user-provided text before it is processed by the logic or returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — accrual-expense-check-free