skills/openclaw/skills/animation-gen/Gen Agent Trust Hub

animation-gen

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill relies on npx ai-animation which downloads the package from the npm registry at runtime. The package is maintained by an external third-party entity ('LXGIC Studios') that is not on the trusted vendor list.- [REMOTE_CODE_EXECUTION]: Executing unversioned packages via npx allows for remote code execution of the latest version available on the registry, which may change without notice.- [COMMAND_EXECUTION]: The core functionality of the skill is built around executing shell commands (npx) provided in the usage instructions.- [PROMPT_INJECTION]: The skill processes untrusted natural language input as a command-line argument for the animation generator. This constitutes an indirect prompt injection surface.
  • Ingestion points: CLI arguments for npx ai-animation take plain English descriptions.
  • Boundary markers: None present in instructions; descriptions are passed directly to the tool.
  • Capability inventory: The tool executes commands, requires an OPENAI_API_KEY (credential access), and likely performs network operations to reach AI providers.
  • Sanitization: No evidence of input validation or sanitization before passing strings to the shell command.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 06:46 PM