cursor-multi-repo

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8).
  • Ingestion points: The skill reads and acts upon project-specific configuration files such as .cursorrules, .cursorignore, and .code-workspace files (SKILL.md, references/multi-root-workspace.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the processed project files.
  • Capability inventory: The skill requests a high level of capability, including Read, Write, Edit, and Bash(cmd:*) permissions (SKILL.md).
  • Sanitization: There is no evidence of content sanitization or validation for the project-level data it processes.
  • [COMMAND_EXECUTION]: The skill requests full Bash access. This is primarily used to facilitate workspace operations, such as invoking the 'cursor' command-line tool to open projects (references/multi-root-workspace.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:11 AM