The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run linear-cli commands. This allows the agent to perform advanced operations such as queries and mutations on the Linear platform as described in the metadata.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it can ingest raw GraphQL queries from external files (e.g., query.graphql). Evidence: 1. Ingestion point: query.graphql via pipe. 2. Boundary markers: Absent. 3. Capability: Subprocess execution of linear-cli with network access. 4. Sanitization: Absent. This surface is inherent to the skill's purpose for raw API access and is considered a low-risk capability.\n- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were detected. The usage of the CLI tool is consistent with the vendor's documentation for Linear API interactions.

linear-api