openmotion-template-to-video

Warn

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The scripts/delivery.mjs script performs dynamic loading of a ZIP utility using import() from a runtimeRoot path computed at execution time. This path is determined by searching for configuration files (openmotion-install.json or scope.json) in the directory hierarchy.
  • [COMMAND_EXECUTION]: The skill instructions regularly direct the agent to execute shell commands using node to run provided scripts (delivery.mjs, playback.mjs, lint-project.mjs) and the hyperframes.mjs engine for rendering and technical checks.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is designed to ingest and interpret data from user-supplied projects.
  • Ingestion points: The skill reads external folders/ZIP files, index.html files, and metadata files like TEMPLATE.md to define project structure and content.
  • Boundary markers: No explicit delimiters or instructions are provided to the model to ignore potential commands embedded within the processed project files.
  • Capability inventory: The skill allows shell command execution, file system modifications, and the creation of a local network listener through the playback.mjs helper.
  • Sanitization: While path traversal is checked in delivery.mjs using the safeRelative function, the skill lacks sanitization for natural language content parsed from metadata files used to influence agent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 20, 2026, 06:53 AM