Skills
skills/1nfsh/skills/talking-head-production/Gen Agent Trust Hub

talking-head-production

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (CRITICAL): The skill instructs the agent to execute curl -fsSL https://cli.inference.sh | sh. This pattern is highly insecure as it executes code from an unverified external domain (inference.sh) directly in the host shell.
  • EXTERNAL_DOWNLOADS (HIGH): The command npx skills add is used to fetch additional functionality from unverified remote repositories, bypassing safety checks.
  • COMMAND_EXECUTION (MEDIUM): The skill utilizes a custom CLI tool (infsh) installed via an insecure method, which is granted broad execution permissions through the Bash(infsh *) configuration.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection.
  • Ingestion points: prompt parameter in dia-tts script.
  • Boundary markers: Absent.
  • Capability inventory: Bash(infsh *) for local execution.
  • Sanitization: Absent.
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 18, 2026, 01:53 AM
Security Audit — agent-trust-hub — talking-head-production