The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various bash commands to analyze the project environment, including find, awk, sed, sort, uniq, and wc. It also performs filesystem modifications using ln -sf to create symbolic links and rm -f to remove existing files (specifically targeting CLAUDE.md).
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It reads existing AGENTS.md and CLAUDE.md files from the user's codebase and extracts insights, conventions, and anti-patterns to generate new documentation.
Ingestion points: Uses Read(filePath=file) to ingest existing documentation files and uses explore agents to scan code comments for patterns like 'DO NOT' or 'NEVER'.
Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts in the ingested content are defined.
Capability inventory: The skill can execute shell commands (bash), spawn sub-agents (Task), and write to the filesystem (Write).
Sanitization: No sanitization or validation of the content read from the codebase is mentioned before it is processed by the agent or sub-agents.

index-knowledge