AGENT LAB: SKILLS

text-to-speech

Fail

Audited by Snyk on Feb 19, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). Although most links are documentation and images on inference.sh, the skill explicitly instructs piping a remote shell script (curl https://cli.inference.sh | sh) from a non-major domain and includes a direct .sh endpoint and a suspicious portrait.jpg URL, which are high-risk indicators for malware distribution.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). Flagged because the Quick Start includes a runtime command that fetches and executes remote code ("curl -fsSL https://cli.inference.sh | sh") and the skill depends on the resulting infsh CLI to run apps (https://cli.inference.sh).
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 19, 2026, 03:40 AM