The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl and jq to interact with the Composio API. These operations are limited to performing authorized actions on the Linear platform and are consistent with the skill's stated purpose.
[EXTERNAL_DOWNLOADS]: All network requests are directed to backend.composio.dev. This is a well-known service used by developers for AI agent tool orchestration and does not constitute a security risk in this context.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its core functionality of reading external data.
Ingestion points: The skill retrieves user-generated content such as issue titles, descriptions, and comments from Linear through various API endpoints.
Boundary markers: The current templates do not use specific delimiters to encapsulate retrieved data.
Capability inventory: The skill utilizes curl for network requests and jq for data processing.
Sanitization: No explicit content sanitization or filtering is performed on the data fetched from the API before it is returned to the agent context.

composio-linear