The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/linear-ready executes linear and jq commands. Input parameters are safely passed to jq using the --arg flag, preventing command injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The documentation identifies @schpet/linear-cli and jq as prerequisites. These are external dependencies that the user is expected to install manually from well-known package registries.
[PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill retrieves issue data from the Linear platform. Since this data is external and potentially attacker-controlled, it represents a surface for indirect prompt injection if the agent follows instructions found within issue titles or descriptions.
Ingestion points: Data is fetched from the Linear API via the linear api command in scripts/linear-ready.
Boundary markers: The output does not use specific delimiters to separate issue content from system instructions.
Capability inventory: The skill facilitates issue updates and status changes using the linear CLI.
Sanitization: The script uses jq to ensure valid JSON processing, but it does not perform natural language sanitization of the issue content.

linear-ready