The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of a global Node.js package using the command npm install -g @optave/codegraph. This package originates from a vendor that is not included in the pre-defined list of trusted organizations or well-known services.
[COMMAND_EXECUTION]: The skill's primary functionality is delivered through the execution of numerous shell commands via bash. These commands interact with the codegraph CLI to index, query, and modify structural maps of a codebase.
[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the local repository to build a structural index, creating a vulnerability surface.
Ingestion points: The codegraph build . command and subsequent scouting commands ingest files and metadata from the current working directory.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to prevent the agent from obeying malicious prompts embedded in the code or comments it analyzes.
Capability inventory: The skill has the ability to execute shell commands and read/write files based on its analysis.
Sanitization: There is no mention of sanitizing or escaping the content of the analyzed files before it is processed by the agent.

codegraph