The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions utilize the Bash tool to run linear-cli for common project management operations like listing, viewing, and creating projects.
[PROMPT_INJECTION]: There is a potential for indirect prompt injection because the skill ingests data from Linear projects which could contain adversarial instructions.
Ingestion points: Project information retrieved from linear-cli p list and linear-cli p get in SKILL.md.
Boundary markers: No specific delimiters or safety instructions are used to separate external project data from the agent's instructions.
Capability inventory: The skill enables the agent to interact with the Linear platform through CLI commands.
Sanitization: The skill lacks mechanisms to sanitize or validate the external data before it is processed by the model.

linear-projects