monorepo-navigator

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill includes instructions in EXTENDED.md to create a Node.js script (scripts/gen-dep-graph.js) using a shell heredoc and then executes it using node. This script utilizes child_process.execSync to invoke workspace tools and fs.writeFileSync to generate documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests metadata from package.json files and pnpm workspace information to perform impact analysis and visualize dependencies.
  • Ingestion points: The skill reads manifest files and pnpm command output to analyze package relationships.
  • Boundary markers: No explicit delimiters or warnings are used to separate untrusted metadata from the agent's instructions.
  • Capability inventory: The skill allows for file writing, shell command execution (via git, turbo, and pnpm), and script execution.
  • Sanitization: Data ingested from workspace manifest files is not validated or sanitized before being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:55 AM
Security Audit — agent-trust-hub — monorepo-navigator