linear
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through data fetched from the Linear API.
- Ingestion points: Content is retrieved from the API in scripts/issues.rb, scripts/issue.rb, scripts/comments.rb, and scripts/search.rb.
- Boundary markers: No delimiters or explicit warnings are used to distinguish external data from agent instructions.
- Capability inventory: The skill allows the agent to execute shell commands (ruby scripts), manage local files, and communicate with the Linear API.
- Sanitization: Content from the API is displayed without escaping or instruction-filtering.
- [DATA_EXFILTRATION]: The skill manages a Linear API token by reading/writing to ~/.config/linear/token. This is intended functionality for communicating with the well-known service api.linear.app. Note that the setup process involves passing the API key as a command-line argument, which may be visible in system process lists.
- [COMMAND_EXECUTION]: The skill executes local Ruby scripts using the standard Ruby interpreter.
Audit Metadata