The Agent Skills Directory

SAFE (SAFE): The skill contains standard command-line interface (CLI) examples for managing labels within Linear. No malicious patterns such as credential exfiltration, remote code execution, or obfuscation were found.- Indirect Prompt Injection (LOW): The skill processes external data such as label IDs and names. While this presents a minor theoretical surface for indirect injection if an attacker-controlled label name is processed by the agent, the skill uses standard bash quoting in its examples, which helps mitigate accidental interpretation of data as commands.

linear-labels