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
beltCLI and suggests adding several related skills from theinference-shandbelt-shGitHub organizations. These are treated as vendor-owned resources supporting the skill's primary function. - Evidence:
npx skills add belt-sh/cliin 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
beltCLI. - Ingestion points: User-provided prompts and input JSON strings used in
belt app runcommands. - 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