batch-linear-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Linear tickets (titles, descriptions, and attachments) which could contain malicious instructions designed to influence the behavior of the agent or its sub-agents.
- Ingestion points: Data enters the context via Linear MCP tools (
mcp__claude_ai_Linear__get_issue) inSKILL.md(Phase 1). - Boundary markers: There is a lack of explicit boundary markers or "ignore instructions" warnings when passing external ticket content to sub-agents like
rca-investigatororaw-planner. - Capability inventory: The workflow leads to code implementation and PR creation via the
aw-executorsub-agent, providing a path from untrusted input to sensitive system operations. - Sanitization: No specific sanitization or filtering of the ticket content is mentioned before it is processed by the sub-agents.
Audit Metadata