skyline-wxss

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the use of npx skyline-cli, which involves downloading and executing an external package from the npm registry. This package is an official tool for the Skyline rendering engine developed by the skill's author, wechat-miniprogram.
  • [COMMAND_EXECUTION]: The skill details several command-line operations using skyline-cli, including wxss list for property discovery and wxss check for syntax validation. These tools are designed for local development and integration with mini-program project environments.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data through the wxss check command.
  • Ingestion points: Untrusted WXSS content is ingested via stdin or specified file paths in SKILL.md (e.g., npx skyline-cli wxss check --files ...).
  • Boundary markers: No explicit delimiting or safety instructions for the processed content are present in the command examples.
  • Capability inventory: The skill uses npx to execute the CLI tool which interacts with the local file system and shell (SKILL.md).
  • Sanitization: The skill assumes the skyline-cli tool provides its own validation and does not specify additional sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:34 PM
Security Audit — agent-trust-hub — skyline-wxss