skills/nanocoai/nanoclaw/add-linear/Gen Agent Trust Hub

add-linear

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches Linear adapter files from a dedicated repository branch (channels) and installs the Node.js package @chat-adapter/linear@4.29.0.
  • [COMMAND_EXECUTION]: Executes shell commands to build the project, run tests, and configure messaging groups using the ncl CLI tool.
  • [PROMPT_INJECTION]: Identified a potential command injection surface where unvalidated user inputs are interpolated directly into shell commands.
  • Ingestion points: User prompts in SKILL.md for linear_team_key and agent_folder.
  • Boundary markers: Absent; inputs are directly placed in command strings without delimiters.
  • Capability inventory: Shell execution via nc:run in SKILL.md.
  • Sanitization: Absent; no validation or escaping is applied to these inputs before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 03:11 AM
Security Audit — agent-trust-hub — add-linear