The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/impact_detector.py script uses the subprocess.run function to execute git diff and git merge-base commands. This is used to identify changed files within the repository for impact analysis. The script correctly uses list-based arguments for the subprocess calls, which prevents shell command injection.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local filesystem during its analysis of monorepo structures.
Ingestion points: scripts/dependency_graph.py, scripts/impact_detector.py, and scripts/package_analyzer.py read content from package.json, pnpm-workspace.yaml, and lerna.json files.
Boundary markers: No specific delimiters or "ignore instructions" warnings are used when the agent processes the output of these tools.
Capability inventory: The tools are capable of reading local files and executing git commands.
Sanitization: The scripts do not perform explicit sanitization of package names or version strings extracted from the configuration files before they are presented to the agent.

monorepo-navigator