product-hunt-launch

Warn

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a remote installation guide containing commands from a non-whitelisted GitHub repository: https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to install and use third-party packages and skills from external, non-trusted sources:
  • npx skills add belt-sh/cli
  • npx skills add inference-sh/skills@ai-image-generation
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its use of web search tools.
  • Ingestion points: The agent retrieves untrusted data from external websites via the tavily/search-assistant and exa/search tools.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to treat data retrieved from search tools as untrusted content.
  • Capability inventory: The skill has access to the Bash(belt *) tool, which allows it to run various sub-applications, search the web, and generate images.
  • Sanitization: There is no evident sanitization or filtering logic applied to the content returned by external search queries.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 6, 2026, 05:02 AM
Security Audit — agent-trust-hub — product-hunt-launch