product-hunt-launch

Fail

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation instructs users to install the CLI tool using curl -fsSL https://cli.inference.sh | sh. This pattern executes a remote script directly in the shell. While the domain is owned by the skill author (tul-sh), this method bypasses standard package management verification. \n- [EXTERNAL_DOWNLOADS]: The installation process downloads architecture-specific binaries from dist.inference.sh at runtime. \n- [COMMAND_EXECUTION]: The skill requires the Bash tool with infsh * permissions, enabling the execution of various CLI sub-commands for image generation and data retrieval. \n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. \n
  • Ingestion points: It retrieves external data via tavily/search-assistant and exa/search to analyze competitors and community sentiment. \n
  • Boundary markers: No explicit delimiters are used to wrap the retrieved web content or instruct the agent to ignore instructions embedded within it. \n
  • Capability inventory: The skill has access to shell execution via the infsh CLI. \n
  • Sanitization: There is no evidence of sanitization or filtering of the external search results before they are processed by the agent.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 4, 2026, 12:29 PM