product-hunt-launch

Fail

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill downloads and executes a script from https://cli.inference.sh by piping it directly into sh. This is a critical risk allowing for arbitrary code execution on the host system.
  • [EXTERNAL_DOWNLOADS]: The skill fetches resources from https://cli.inference.sh, which is an untrusted external domain not included in the trusted vendors list.
  • [COMMAND_EXECUTION]: The skill executes the infsh and npx commands to interact with external services and install additional skills.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to its data ingestion patterns.
  • Ingestion points: The skill pulls data from external search providers via the tavily/search-assistant and exa/search tools.
  • Boundary markers: No delimiters or instructions are used to separate untrusted search results from system instructions.
  • Capability inventory: The skill has access to the Bash tool, which could be exploited if malicious commands are returned in search results.
  • Sanitization: There is no evidence of sanitization or validation of the content returned from external search tools.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 14, 2026, 06:27 AM