xyq-skill
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script
ensure-cli.jsis designed to download and update the toolkit from the official@pippit-dev/clipackage on npm, ensuring the latest features and security updates are present. - [REMOTE_CODE_EXECUTION]: During initial setup or updates, the skill executes a platform-specific installer script included within the vendor's npm package to prepare the binary environment.
- [COMMAND_EXECUTION]: The skill manages media tasks by executing local commands via the
pippit-tool-clibinary and Node.js runtime, which are required for generative image and video processing. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge for user-supplied prompts to be processed by generative models, creating a potential surface for instructions embedded in data.
- Ingestion points: User-provided creative prompts and local media file paths processed in the image and video generation modules.
- Boundary markers: The skill uses structured CLI flags (e.g.,
--prompt) to delimit user content from command logic. - Capability inventory: The skill possesses file system access for media processing and cache management, network access for media uploading and status checks, and command execution capabilities.
- Sanitization: Instructions explicitly forbid the agent from modifying or expanding the user's prompt, relying on the underlying service's internal validation for safety.
Audit Metadata