The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data from external Linear sources which may contain malicious instructions targeting the agent.
Ingestion points: Untrusted content is ingested from Linear issue descriptions, comments, and attachments via linear-cli commands (SKILL.md).
Boundary markers: The instructions do not define delimiters or provide warnings to ignore embedded instructions within the fetched data.
Capability inventory: The agent uses Bash to run linear-cli and the Read tool to process downloaded files, creating a path for automated actions based on external input.
Sanitization: There is no evidence of filtering or sanitizing the input from Linear before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill downloads content from an external domain.
Evidence: The linear-cli up fetch command is used to download files from uploads.linear.app (SKILL.md).
Note: The source is a well-known service associated with the Linear project management platform.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the linear-cli utility.
Evidence: Multiple examples use linear-cli for fetching data, listing comments, and getting issue details (SKILL.md).

linear-uploads