effectcraft-logo-reveal

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several external resources for documentation and configuration, such as 'github.com/storytold/effectcraft', 'github.com/dylantarre/animation-principles', and 'github.com/docsforadobe/after-effects-scripting-guide'. These are documented as sources for workflow facts and technical parameters and do not involve the execution of untrusted remote code.
  • [COMMAND_EXECUTION]: The skill documents the use of 'effectcraft-cli' and local MCP tools ('command_run'). These commands are scoped to the primary purpose of the skill (video/animation editing) and operate on local project files within the user's control. An installation command for 'effectcraft-editor' using 'npx' is mentioned but presented as an optional, manual step for the user rather than an automated execution.
  • [DATA_EXPOSURE]: There is no evidence of the skill accessing sensitive system files (e.g., SSH keys, AWS credentials) or environment variables. All file operations (save_project, save_file) are directed toward project-specific animation assets and configuration.
  • [PROMPT_INJECTION]: The instructions follow standard task-oriented patterns without attempting to override system safety guidelines or extract underlying prompts.
  • [METADATA_POISONING]: Metadata fields (name, description, license) are consistent with the content of the skill and do not contain deceptive instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 09:36 AM