mdcp-getting-started

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @bwilliamson/mdcp-cli and @bwilliamson/mdcp-presets packages via the project's package manager. These packages are authored by the skill's creator and are integral to the documentation system.
  • [COMMAND_EXECUTION]: The agent is instructed to run shell commands including npm install, mdcp compile, and mdcp check to establish the documentation environment and validate content.
  • [PROMPT_INJECTION]: The skill includes instructions to ingest and migrate "legacy docs" from existing repositories.
  • Ingestion points: The agent reads markdown files from the documentation tree during the brownfield migration process.
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within the legacy documentation content.
  • Capability inventory: The skill has the ability to write files, install external packages, and execute the mdcp CLI tool.
  • Sanitization: There is no specified logic for sanitizing or filtering the content extracted from external documentation files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 09:49 PM
Security Audit — agent-trust-hub — mdcp-getting-started