Linear Automation

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting and processing untrusted external data within its workflows.
  • Ingestion points: SKILL.md (Processes issue details, cycle configurations, project milestones, team assignments, and GitHub pull request data).
  • Boundary markers: Absent (The skill interpolates user-controlled data directly into templates without using delimiters or instructions to ignore embedded commands).
  • Capability inventory: SKILL.md (Available tools include linear_create_issue, linear_update_issue, linear_search, and linear_cycles, which allow for state modification within the Linear platform).
  • Sanitization: Absent (No explicit escaping, validation, or sanitization logic is described for variables like {{description}}, {{tech_notes}}, or {{attachments}} before they are processed by the agent).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 02:51 PM
Security Audit — agent-trust-hub — Linear Automation