explainer-video-guide
Fail
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- REMOTE_CODE_EXECUTION (CRITICAL): The command 'curl -fsSL https://cli.inference.sh | sh' downloads and executes a script from the internet directly in the shell. Since 'inference.sh' is not a verified trusted source, this allows for potential full system compromise.
- EXTERNAL_DOWNLOADS (MEDIUM): The skill uses 'npx skills add' to fetch and install external skills from 'inference-sh/skills'. This introduces third-party code from unverified sources into the environment.
- COMMAND_EXECUTION (LOW): The skill utilizes the 'infsh' command-line tool for various media generation tasks. While this is the intended functionality, it relies on the safety of the previously installed (untrusted) CLI tool.
- PROMPT_INJECTION (LOW): The skill interpolates user-provided text prompts into shell commands. This creates an indirect prompt injection surface where malicious input could potentially attempt to escape the command structure or influence the generated output. Evidence: Prompt interpolation in 'infsh' calls in SKILL.md.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata