resolve-linear-issue
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands for code validation and project management, including linting, typechecking, and testing with tools like pnpm, vitest, turbo, and biome. It also utilizes the GitHub CLI (gh) for branch management and pull request creation.
- [EXTERNAL_DOWNLOADS]: Retrieves design specifications and project artifacts from official and well-known services including Linear and Anthropic's Claude.ai.
- [PROMPT_INJECTION]: Contains a surface for indirect prompt injection as it processes untrusted data from issue descriptions and external links. The skill includes a specific directive to treat fetched content as data rather than instructions to mitigate this risk. Ingestion points: Linear issues, plan files, and design artifacts. Boundary markers: Explicit instructions to treat content as data are present. Capability inventory: Includes file system writes, shell command execution, and GitHub operations. Sanitization: Relies on the agent's internal reasoning and behavioral instructions.
Audit Metadata