product-hunt-launch

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute belt commands. These commands interact with the inference.sh platform to perform tasks such as image generation and web searches.\n- [EXTERNAL_DOWNLOADS]: The skill references a GitHub repository for CLI installation instructions and allows adding further functional skills from the inference-sh organization via npx.\n- [PROMPT_INJECTION]: The skill processes external web data via search tools, presenting a surface for indirect prompt injection.\n
  • Ingestion points: The commands belt app run tavily/search-assistant and belt app run exa/search in SKILL.md fetch content from external websites.\n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore embedded instructions.\n
  • Capability inventory: Access to the belt CLI provides interaction capabilities with the vendor's platform, including image generation and further searches.\n
  • Sanitization: No sanitization or filtering logic is present for the ingested search results before they are returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 03:53 PM
Security Audit — agent-trust-hub — product-hunt-launch