ai-video-generation

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the belt CLI and suggests adding several related skills from the inference-sh and belt-sh GitHub organizations. These are treated as vendor-owned resources supporting the skill's primary function.
  • Evidence: npx skills add belt-sh/cli in SKILL.md
  • Evidence: npx skills add inference-sh/skills@... (multiple variants) in SKILL.md
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection (Category 8) because it ingests untrusted user text (prompts) and interpolates them into shell commands for the belt CLI.
  • Ingestion points: User-provided prompts and input JSON strings used in belt app run commands.
  • Boundary markers: None identified; instructions do not specify the use of delimiters or warnings to ignore embedded instructions within user-provided prompts.
  • Capability inventory: The skill utilizes Bash(belt *) to execute commands, which includes the ability to process network-connected AI inference tasks.
  • Sanitization: No sanitization or escaping mechanisms are described for handling special characters or command injection sequences within the user-supplied prompt strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:17 PM
Security Audit — agent-trust-hub — ai-video-generation