Skills
skills/neversight/skills_feed/ai-avatar-video/Gen Agent Trust Hub

ai-avatar-video

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION] (CRITICAL): The installation instructions in SKILL.md suggest running curl -fsSL https://cli.inference.sh | sh, which downloads and executes a shell script from an untrusted third-party domain, allowing for arbitrary code execution.
  • [EXTERNAL_DOWNLOADS] (HIGH): The skill downloads and executes unverified CLI tools and additional components via npx without integrity verification or version pinning.
  • [COMMAND_EXECUTION] (MEDIUM): The skill requires permission to execute infsh commands via the Bash tool, which provides a broad interface for interacting with remote services and local data.
  • [PROMPT_INJECTION] (HIGH): The skill exhibits a significant indirect prompt injection surface (Category 8). 1. Ingestion points: Untrusted inputs from image_url, audio_url, and text fields. 2. Boundary markers: Absent. 3. Capability inventory: Use of infsh for media generation and transcription. 4. Sanitization: Absent for external data and URLs. This vulnerability could allow malicious content embedded in media or text to compromise the downstream generation process.
Recommendations
  • CRITICAL: Downloads and executes remote code from untrusted source(s): https://cli.inference.sh - DO NOT USE
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 06:52 AM