The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the monorepo being analyzed, which could theoretically contain malicious instructions. However, this is expected behavior for a repository analysis tool.
Ingestion points: The monorepo_analyzer.py script reads and parses package.json and pnpm-workspace.yaml files within the target directory.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used in the analysis flow.
Capability inventory: The skill utilizes subprocess execution for monorepo CLI tools (pnpm, nx, turbo) and provides scripts for file system analysis.
Sanitization: Data is parsed as JSON and text; no specific sanitization for prompt injection or command sequences is implemented.
[COMMAND_EXECUTION]: The skill utilizes and provides instructions for executing standard monorepo management CLI tools (pnpm, nx, turbo, lerna). All commands identified are common development tools used for building, testing, and managing workspaces.
[DYNAMIC_EXECUTION]: The skill provides a JavaScript utility (scripts/gen-dep-graph.js) that uses execSync to run CLI commands for dependency visualization. This is a common pattern for local developer tooling.

monorepo-navigator