linear-monitor
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project data from Linear issues, comments, and documents which are considered untrusted sources. This creates a surface for indirect prompt injection attacks. However, the methodology (Section 0) explicitly defines a trust boundary, instructing the agent to treat this content as data only and to disregard any instructions or commands embedded within project files.
- [SAFE]: The skill relies on official Linear MCP tools for all operations. It explicitly warns against using unofficial wrappers, GraphQL, or direct curl commands for authentication.
- [SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalations were found in the instructions or methodology.
Audit Metadata