AGENT LAB: SKILLS

pitch-deck-visuals

Fail

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION] (CRITICAL): Piped remote script execution detected using the pattern curl -fsSL https://cli.inference.sh | sh. This allows an external, unverified script to run directly on the host system.
  • [EXTERNAL_DOWNLOADS] (HIGH): The skill attempts to download resources from https://cli.inference.sh, which is not a recognized trusted source, increasing the risk of supply chain attacks.
  • [COMMAND_EXECUTION] (HIGH): The use of a shell pipe to execute remote content bypasses standard verification processes and is a high-risk command execution pattern.
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