linear

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from data retrieved from the Linear API.\n
  • Ingestion points: Issue data, descriptions, and comments are fetched from the Linear API and displayed to the agent in scripts/linear.ts (e.g., in cmdIssue and cmdSearch).\n
  • Boundary markers: No delimiters or explicit instructions to ignore embedded content are used when outputting retrieved data.\n
  • Capability inventory: The skill possesses the ability to create, update, and delete records (issues, labels, docs) on the Linear platform via the SDK.\n
  • Sanitization: No sanitization or validation of the API response data is performed before presentation.\n- [SAFE]: The skill uses the official @linear/sdk, which is a well-known and trusted dependency.\n- [SAFE]: Linear API credentials are correctly managed through environment variables (LINEAR_API_KEY), avoiding the risk of hardcoded secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 05:27 AM