The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes shell commands such as nx, turbo, and git, and executes a local Python script scripts/monorepo_analyzer.py. This script is missing from the provided files, which prevents a full security assessment of its operations.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection when analyzing monorepo directories. Ingestion points: Monorepo configuration and project files are scanned using the analyzer script and the CLAUDE.md patterns. Boundary markers: The skill contains a rule to treat workspace content as data, but this does not prevent an LLM from potentially following instructions found within those files. Capability inventory: The skill can execute commands and read/write files. Sanitization: No specific content sanitization or isolation measures are described.

monorepo-navigator