markstream-install

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files such as package.json and application entry points to make installation decisions.
  • Ingestion points: package.json and application entry files.
  • Boundary markers: None present to delimit code-originated data from instructions.
  • Capability inventory: File system write access and execution of package installation commands.
  • Sanitization: No explicit sanitization of input read from configuration files.
  • [COMMAND_EXECUTION]: The workflow involves the execution of package manager commands (e.g., npm install) and project build/test scripts.
  • [EXTERNAL_DOWNLOADS]: The skill guides the installation of several well-known peer dependencies including mermaid, katex, @antv/infographic, and @terrastruct/d2.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 11:31 PM