linear-relations

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (MEDIUM): The skill uses the Bash tool to execute linear-cli. It lacks sanitization for issue IDs and relation types, which could allow shell injection if the agent blindly interpolates user input.
  • [INDIRECT_PROMPT_INJECTION] (MEDIUM): This skill handles external identifiers and possesses command execution capabilities. 1. Ingestion points: User-provided issue IDs and relation types. 2. Boundary markers: Absent. 3. Capability inventory: Shell execution via Bash. 4. Sanitization: None detected in the skill instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:57 AM