The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing the linear CLI tool to perform various project management tasks, including issue creation, updates, and deletions.
[EXTERNAL_DOWNLOADS]: The instructions direct the user to install the @injectivelabs/linear-cli package via NPM or download binaries from the vendor's GitHub repository (github.com/InjectiveLabs/linear-cli).
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted data from an external platform.
Ingestion points: Untrusted data enters the agent context through commands like linear issue view, linear issue list, and linear document view which read issue content and comments.
Boundary markers: There are no explicit instructions or delimiters defined to distinguish external platform data from the agent's internal instructions.
Capability inventory: The skill has the capability to write and delete data on the Linear platform through commands such as linear issue create, linear issue update, linear issue comment add, and linear issue delete.
Sanitization: No evidence of data sanitization or filtering of external content is provided in the skill documentation.
[CREDENTIALS_UNSAFE]: The skill requires a LINEAR_API_KEY for authentication. It instructs users to export the key as an environment variable and includes the command linear auth token, which displays the active API token in the terminal output.

linear-cli