product-hunt-launch

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to execute specific applications for generating product mockups and conducting research. These operations are core to the skill's utility.\n- [EXTERNAL_DOWNLOADS]: References installation instructions from the vendor's GitHub repository and utilizes npx to install supplementary skills. These are standard setup procedures for the toolset.\n- [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill ingests results from external search engines (Tavily and Exa).\n
  • Ingestion points: Competitive research data from search providers enters the agent's context.\n
  • Boundary markers: None explicitly provided in the instruction set.\n
  • Capability inventory: The agent can execute commands via belt and install further extensions via npx.\n
  • Sanitization: No specific filtering of external search results is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 03:28 AM
Security Audit — agent-trust-hub — product-hunt-launch