The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the npm registry. This is a vendor-owned tool required for the skill's operation with the Membrane platform.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform various tasks including login, connection management, and action execution. These commands are part of the intended project management workflow.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from GitHub.
Ingestion points: External data enters the agent context through GitHub issue and pull request descriptions, titles, and comments retrieved via various 'list' and 'get' actions.
Boundary markers: The instructions do not define explicit delimiters or 'ignore' warnings for the data being processed.
Capability inventory: The skill has the ability to perform write operations on GitHub, such as creating issues, updating pull requests, and merging code through membrane action run commands.
Sanitization: There is no evidence of sanitization or validation of the content retrieved from GitHub before it is processed by the agent.

github