fx-settlement-check-free

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md file includes a text block specifically crafted for the AI assistant that uses deceptive authorization language ('I have authorized installation') to bypass user confirmation for software installation and payments.
  • [COMMAND_EXECUTION]: The skill's documentation provides the shell command npx -y @alipay/agent-payment@latest install and instructs the agent to run it, granting the skill the ability to execute arbitrary code and modify the system.
  • [REMOTE_CODE_EXECUTION]: The suggested command uses npx to fetch and execute external code from a remote registry at runtime, which is an insecure practice when triggered by agent instructions rather than explicit user action.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — fx-settlement-check-free