The Agent Skills Directory

[SAFE]: The skill uses allowed Bash tools to execute commands for importing and exporting data using a command-line interface. All operations are consistent with the stated purpose of bulk-creating issues.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external CSV and JSON data files.
Ingestion points: The agent reads issues.csv and issues.json to perform imports via linear-cli.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious embedded instructions within the data files.
Capability inventory: The skill has the capability to perform network operations and modify external state through the linear-cli tool.
Sanitization: The skill does not implement its own sanitization, relying instead on the input validation of the linear-cli tool.

linear-import