The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Recommends the installation of the linearis package from the npm registry. This tool is a community-maintained CLI used to interact with the Linear API.
[COMMAND_EXECUTION]: The skill relies on executing shell commands through the linearis CLI for ticket operations and jq for parsing and filtering the resulting JSON data.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes issue descriptions and comments which originate from external users and are potentially untrusted.
Ingestion points: Issue descriptions and comments retrieved from linearis issues read, list, and search commands.
Boundary markers: Absent; ticket content is interpolated directly into the debugging context and shell variables (e.g., ISSUE_DESC).
Capability inventory: The skill has the ability to execute shell commands (linearis, jq) and write files to the local file system.
Sanitization: No sanitization, escaping, or validation is performed on the retrieved ticket content before it is displayed or processed.
[DATA_EXFILTRATION]: The skill frequently writes Linear issue data to the /tmp directory (e.g., /tmp/linear-issues-$(date +%Y%m%d).json). This exposes potentially sensitive project information to other users or processes on the same system.

linear-issues