linear-documents

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the linear-cli tool to interact with Linear's document API. It performs standard operations such as listing, getting, creating, and updating documents.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external data from Linear documents, which presents an attack surface for indirect prompt injection.
  • Ingestion points: The agent reads document content and lists via linear-cli d list and linear-cli d get (SKILL.md).
  • Boundary markers: None identified. There are no instructions to treat the retrieved content as untrusted data or to ignore embedded commands.
  • Capability inventory: The skill has access to the Bash tool, allowing for broad command execution based on processed data.
  • Sanitization: No sanitization, escaping, or validation of the retrieved document content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:13 AM
Security Audit — agent-trust-hub — linear-documents