ai-video-generation

Fail

Audited by Snyk on May 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 set includes an instruction to curl a remote installer and pipe it to sh (https://cli.inference.sh | sh), plus personal/cloud file-hosting links and several non-verified media hosts, which together create a high risk of arbitrary/hidden code execution or malware distribution even though many URLs are just docs or media placeholders.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs using inference.sh with user-provided public URLs (e.g., the examples with "image_url", "audio_url", and "video_url" in SKILL.md) so the agent will fetch and process arbitrary third‑party content from the open web which could embed instructions that influence generation behavior.

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

  • Potentially malicious external URL detected (high risk: 1.00). The Quick Start instructs users to run "curl -fsSL https://cli.inference.sh | sh", which fetches and immediately executes remote shell code from https://cli.inference.sh and is required to install/run the infsh CLI used by the skill, so this is a runtime external dependency that executes remote code.

Issues (3)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
May 19, 2026, 03:13 PM
Issues
3
Security Audit — snyk — ai-video-generation