The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to search and retrieve data from GitHub, including code, issues, and pull requests. This content is externally controlled and untrusted.
Ingestion points: Data enters the agent's context through the output of various gh search commands described in SKILL.md.
Boundary markers: There are no specific instructions or delimiters mentioned to help the agent distinguish between search metadata and potentially malicious instructions embedded within the retrieved GitHub content.
Capability inventory: The skill utilizes the gh CLI for searching and suggests integration with other skills like repository-management or code-review which likely have file-write or execution capabilities.
Sanitization: The skill does not describe any sanitization or filtering mechanisms for the data retrieved from GitHub before it is processed by the agent.
[COMMAND_EXECUTION]: The skill revolves around the execution of the gh CLI tool. While the examples provided use standard parameters, there is a risk of command injection if the agent interpolates unsanitized user input into these search commands, particularly within the query strings or jq filters.

search-operations