The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to perform GraphQL queries and mutations against the Linear API. This is the primary mechanism for all operations.\n- [EXTERNAL_DOWNLOADS]: Communicates with https://api.linear.app/graphql. This is a well-known service and the operation is considered safe.\n- [PROMPT_INJECTION]: The skill ingests and processes untrusted data (issue titles, descriptions, and comments) retrieved from the Linear API. This creates a surface for indirect prompt injection where malicious content within a Linear issue could attempt to manipulate the agent's instructions.\n
Ingestion points: API responses from api.linear.app containing user-generated content such as issue descriptions and comments.\n
Boundary markers: Absent; the skill provides raw command templates without instruction delimiters or warnings to ignore embedded content.\n
Capability inventory: The agent uses curl to fetch and submit data, and processes JSON output using python3 -m json.tool.\n
Sanitization: No explicit sanitization or validation of the retrieved content is performed before it is presented to or processed by the agent.

linear