batch-linear-tickets

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted input from Linear tickets (titles, descriptions, and labels) and uses this data to drive autonomous planning and execution phases. This creates an indirect prompt injection surface where malicious ticket content could override agent instructions.
  • Ingestion points: Data enters the workflow in SKILL.md (Phase 1a) via Linear MCP tools like mcp__claude_ai_Linear__get_issue.
  • Boundary markers: The skill lacks explicit delimiters (e.g., XML tags) or "ignore embedded instructions" warnings when interpolating ticket data into the analysis and planning templates such as feature-pack.md.
  • Capability inventory: The workflow dispatches aw-planner and aw-executor agents, which have the capability to modify the codebase, create worktrees, and open pull requests via the gh CLI.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the external content retrieved from Linear before it is passed to downstream agents.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 11:46 AM
Security Audit — agent-trust-hub — batch-linear-tickets