linear-implement

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows secure development practices by using isolated git worktrees for implementation tasks and enforcing a multi-lens review process before finalization.
  • [COMMAND_EXECUTION]: The skill utilizes local TypeScript scripts and git commands to automate workspace validation and handoff verification. These operations are performed locally and are restricted to project-specific tasks.
  • [PROMPT_INJECTION]: The skill processes implementation plans from Linear issue comments, which represents a surface for indirect prompt injection. This risk is mitigated through several mechanisms: 1. Ingestion points: Data enters the context via Linear issue descriptions and comments. 2. Boundary markers: The skill uses specific HTML comment blocks to delimit machine-readable instructions. 3. Capability inventory: The agent can modify files, run tests, and update Linear status. 4. Sanitization: Extracted instructions are validated against predefined YAML schemas using the AJV validation library to ensure structure and prevent unexpected command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 11:49 AM
Security Audit — agent-trust-hub — linear-implement