export-fx-collection-check-free

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The SKILL.md file contains a specific instruction block for the agent to install an external payment package (npx -y @alipay/agent-payment@latest install) and to purchase a full version of the tool using merchant and product identifiers. If the AI agent reads these instructions as part of its context, it may attempt to execute these commands or initiate the purchase flow without direct user triggering.\n
  • Ingestion points: The body of the SKILL.md file.\n
  • Boundary markers: The instructions are provided without delimiters or warnings to prevent autonomous execution by the agent.\n
  • Capability inventory: The skill is granted the Bash tool, which is necessary to execute the npx command suggested in the text.\n
  • Sanitization: No sanitization is performed on the instruction text provided for the agent.\n- [EXTERNAL_DOWNLOADS]: The documentation refers to the installation of an external package (@alipay/agent-payment) and provides links to a well-known fintech service provider (Alipay) for payment processing. These references are documented neutrally as they originate from a well-known service.\n- [COMMAND_EXECUTION]: The skill requires the Bash tool to execute the local auditing engine via node scripts/run.mjs. It also suggests the execution of npx commands within the agent's environment to facilitate tool installation and purchases.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — export-fx-collection-check-free