The Agent Skills Directory

[DATA_EXFILTRATION]: The skill communicates with the official Linear API (https://api.linear.app/graphql). This is a well-known service and the interaction is required for the skill's core functionality. No sensitive local files are accessed or transmitted.\n- [PROMPT_INJECTION]: The skill ingests issue data from an external source (Linear). While this creates a surface for indirect prompt injection, it is the primary purpose of the skill and is handled via structured JSON output. Ingestion points: Linear issue titles and descriptions; Boundary markers: JSON output structure; Capability inventory: Linear API write operations; Sanitization: Descriptions are truncated to 200 characters.\n- [SAFE]: The skill uses only Python's standard library and does not include any third-party dependencies, obfuscation, or persistence mechanisms.

linear-skill