AGENT LAB: SKILLS

ai-social-media-content

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 URLs point to an unverified/unknown domain and the skill explicitly instructs piping a remote shell script (curl ... https://cli.inference.sh | sh) for direct execution—an inherently high‑risk pattern (plus a placeholder avatar URL and hosted image that could host malicious payloads or be used for tracking).

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

  • Potentially malicious external URL detected (high risk: 1.00). The Quick Start uses a runtime command that fetches and executes remote code ("curl -fsSL https://cli.inference.sh | sh"), which installs/controls the required infsh CLI used throughout the skill, so https://cli.inference.sh is a high-risk external dependency.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 19, 2026, 03:40 AM