AGENT LAB: SKILLS

product-hunt-launch

Fail

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION] (CRITICAL): The skill instructs the user to execute 'curl -fsSL https://cli.inference.sh | sh'. This piped-to-shell pattern executes remote code without integrity verification or source authentication, posing a severe risk.
  • [EXTERNAL_DOWNLOADS] (HIGH): The skill downloads and installs a CLI tool and additional packages from 'inference.sh', which is not a verified trusted source.
  • [COMMAND_EXECUTION] (HIGH): The tool 'Bash(infsh *)' allows for the execution of arbitrary commands through an unverified CLI interface.
  • [PROMPT_INJECTION] (LOW): Indirect prompt injection surface identified. 1. Ingestion points: Data entering via 'tavily/search-assistant' and 'exa/search'. 2. Boundary markers: None. 3. Capability inventory: Command execution via 'infsh' and 'Bash'. 4. Sanitization: No sanitization of external search results before use in subsequent commands.
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
Feb 19, 2026, 03:41 AM