budget-variance-check-free

Fail

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: HIGHPROMPT_INJECTIONREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md file contains a pre-written message block intended for the user to provide to their AI assistant. This message includes instructions that attempt to override the agent's standard security and confirmation protocols by claiming the user has already authorized the installation of remote dependencies and the initiation of purchases ('I have authorized... need no confirmation...'). This is a social engineering pattern designed to bypass interactive safety checkpoints.
  • [REMOTE_CODE_EXECUTION]: The skill documentation instructs the execution of npx -y @alipay/agent-payment@latest install, which downloads and executes a package from the npm registry. While the package is associated with a well-known service (Alipay), the use of the -y flag combined with instructions to the agent to skip confirmation increases the risk profile.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run Node.js scripts (scripts/run.mjs) for local processing of budget data files.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — budget-variance-check-free