product-hunt-launch
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to prerequisite installation instructions hosted on GitHub under the inference-sh repository.
- [COMMAND_EXECUTION]: The skill utilizes the 'belt' CLI tool to execute specific sub-commands for authentication, image generation, and search, involving network activities with external AI providers.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external web searches via 'tavily/search-assistant', creating an attack surface where third-party content could contain malicious instructions.
- Evidence: The workflow uses search results to summarize competitors and top launches.
- Capability Tier: Tier 2 (Ability to execute shell commands and call external APIs via CLI).
- Recommendation: Verify and sanitize search result content before processing to prevent the agent from following embedded adversarial instructions.
Audit Metadata