viral-script-free

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install a tool using the command npx -y @alipay/agent-payment@latest install. This references a package from the official scoped namespace of a well-known service provider on the NPM registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill's documentation contains a pre-formatted text block designed for the user to submit to an AI agent. This block provides instructions to guide the agent through an external installation and purchase workflow.
  • Ingestion points: The SKILL.md file provides specific text meant to be processed as instructions by an AI assistant.
  • Boundary markers: The provided text block does not use explicit boundary markers to isolate the user-provided prompt from existing agent instructions.
  • Capability inventory: The skill relies on the Bash tool to execute its local Node.js analysis engine, while the documentation prompts the use of external shell tools.
  • Sanitization: The skill involves manual user participation for the upgrade instructions; no automated sanitization of the provided prompt block is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — viral-script-free