storyboard-creation

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the belt-sh/cli tool and references several related skills from the inference-sh organization on GitHub (e.g., inference-sh/skills@ai-image-generation). These are the primary tools required for the skill to perform its intended task of AI image generation.
  • [COMMAND_EXECUTION]: The skill utilizes the belt command-line interface to execute tasks on remote models, such as falai/flux-dev-lora for image generation and infsh/stitch-images for layout assembly. These commands are typical for the skill's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided natural language descriptions to generate storyboard panels, creating an attack surface where malicious input could influence the image generation tool.
  • Ingestion points: User-provided strings are interpolated into the --input JSON object for the belt command in SKILL.md.
  • Boundary markers: None identified; input is passed directly into the tool's prompt field.
  • Capability inventory: The skill is limited to executing the belt tool via Bash as defined in the allowed-tools frontmatter.
  • Sanitization: No sanitization or validation of the input strings is performed before they are sent to the remote API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — storyboard-creation