AGENT LAB: SKILLS

ai-podcast-creation

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). The domain hosts an undocumented CLI installer and the skill instructs piping a remote script (curl https://cli.inference.sh | sh) — a high-risk pattern for distributing malware even if the image URL itself is benign, because executing an unverified .sh from an unknown/untrusted domain can run arbitrary code on your machine.

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

  • Potentially malicious external URL detected (high risk: 1.00). Flagging https://cli.inference.sh because the Quick Start includes "curl -fsSL https://cli.inference.sh | sh" which fetches and executes remote code at runtime and is presented as a required installation step for using the skill.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 19, 2026, 03:40 AM