linear-projects

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute linear-cli commands, enabling full project management operations including creation, modification, and deletion.
  • [PROMPT_INJECTION]: The skill ingests untrusted project data (names, descriptions, and member information) from the Linear API, which represents an indirect prompt injection attack surface.
  • Ingestion points: Project content and metadata retrieved via linear-cli p list, linear-cli p get, and linear-cli p members as described in SKILL.md.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to isolate data from potential instructions within the project content.
  • Capability inventory: The skill utilizes Bash for command execution, providing a capability that could be targeted if malicious instructions are processed.
  • Sanitization: No evidence of data validation, filtering, or sanitization is present in the instructions for handling the external API output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:14 AM
Security Audit — agent-trust-hub — linear-projects