linear-search
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (LOW): The skill retrieves external data from Linear.app which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: linear-cli s issues, linear-cli i get (SKILL.md).
- Boundary markers: Absent in provided examples.
- Capability inventory: Bash command execution (linear-cli).
- Sanitization: None specified in instructions.
Audit Metadata