The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides specific guidance on executing gitquarry CLI commands to perform repository search, inspection, code lookup, and authentication management.
[EXTERNAL_DOWNLOADS]: The skill includes instructions to fetch and load version-matched skill definitions using the gitquarry skills get gitquarry command, which constitutes a remote download of instruction content.
[PROMPT_INJECTION]: The skill is designed to process untrusted data from external GitHub repositories, such as README files and source code, creating an attack surface for indirect prompt injection.
Ingestion points: The skill retrieves file trees, source code, and repository documentation (READMEs) through the search, inspect, and code commands.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions within the retrieved external content to prevent the agent from obeying embedded commands.
Capability inventory: The agent is authorized to use gitquarry:* tools, which have access to the network (GitHub API) and local configuration files.
Sanitization: No specific sanitization or filtering logic is described for the content ingested from remote repositories before it is processed by the agent.

gitquarry-operator