The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill executes multiple inline Python scripts using the `python3
<<'PY'andpython3 -cpatterns to parse JSON configuration files like.mcp.jsonand.claude/settings.json. This is used to extract hook registrations and transport settings for diagnostic purposes.\n- **[COMMAND_EXECUTION]:** The skill uses bash commands to inspect the local file system, check git hook status, and detect the presence of specific Node.js modules and CLI tools (e.g., claude --version, git rev-parse`).\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external project files which could potentially contain malicious instructions meant to influence the agent's diagnostic output.\n
Ingestion points: CLAUDE.md, .claude/skills/*/SKILL.md, .mcp.json, .claudeignore, and various audit/log files found via find.\n
Boundary markers: No specific boundary markers or instructions to ignore embedded commands were found in the processing logic.\n
Capability inventory: The skill uses Bash, Read, Glob, and Grep to access and process the ingested data.\n
Sanitization: The skill does not perform explicit sanitization or escaping of the content read from the file system before including it in the logic or diagnostic report.

install-doctor