moda-video-clip

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user descriptions and external brand metadata into generation prompts and CLI commands without the use of boundary markers or sanitization logic.
  • Ingestion points: User prompts provided via argument hints and brand asset metadata retrieved via the moda brand show command are interpolated into video generation tasks.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided templates.
  • Capability inventory: The skill utilizes Bash(moda:*) which provides extensive file system access, network operations for media fetching, and canvas manipulation.
  • Sanitization: There is no evidence of input validation or sanitization before data is passed to tool calls.
  • [DYNAMIC_EXECUTION]: The skill utilizes a JavaScript-based batch editor to manipulate canvas objects at runtime.
  • Evidence: As detailed in references/edit-code.md, the moda canvas edit command executes synchronous JavaScript code to mutate existing nodes and pages. This behavior is inherent to the primary purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 11:46 PM
Security Audit — agent-trust-hub — moda-video-clip