The Agent Skills Directory

[SAFE]: The skill provides documentation for the indexion CLI tool, which is used for local codebase search and structural analysis. The tool operates on local directories such as src/ and cmd/. No malicious intent or dangerous exfiltration patterns were identified.- [COMMAND_EXECUTION]: The skill instructs the agent to use indexion commands (e.g., indexion grep, indexion digest, indexion search) and standard shell utilities like cat for file comparison. These are expected behaviors for a codebase analysis skill.- [PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection by enabling the agent to read and process content from local files that could be controlled by an external actor.
Ingestion points: File content from target directories (src/, cmd/, .indexion/wiki/) read by indexion grep, indexion search, and indexion digest commands.
Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for the data being searched.
Capability inventory: The skill utilizes subprocess calls to execute the indexion tool, which performs file reading and manages a local metadata cache.
Sanitization: The skill does not implement specific sanitization for the codebase content it processes.

indexion-search