linear-bootstrap

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied natural language descriptions to generate project structures, creating a surface for indirect prompt injection.
  • Ingestion points: Project descriptions are gathered from the $ARGUMENTS variable as described in the workflow section of SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the project description.
  • Capability inventory: The skill utilizes the mcp__linear-bootstrap__bootstrap-project tool to write data (projects, issues, etc.) directly to the Linear platform.
  • Sanitization: There is no evidence of input validation or sanitization of the description before it is passed to the plan generation tools.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions for manual verification and troubleshooting using the vendor's own package.
  • Evidence: Suggests running npx @toolwright-adk/linear-bootstrap if the MCP server is unavailable. This is a legitimate vendor-owned resource matching the author 'toolwright-adk'.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 04:38 PM