The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill content.
[COMMAND_EXECUTION]: The skill uses the Bash tool to interact with the linear-cli tool. The commands are standard administrative operations for webhook management (list, create, get, update, delete, rotate-secret, listen).
[PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection via the 'wh listen' command, which receives external webhook events. This is an architectural feature of the tool's intended use and includes mitigation options. * Ingestion points: Local server listening on port 9000 (SKILL.md). * Boundary markers: None explicitly defined in the CLI instructions. * Capability inventory: Bash command execution for linear-cli subcommands. * Sanitization: The skill documentation explicitly supports HMAC verification via the '--secret' flag to validate the authenticity of incoming events.

linear-webhooks