cursor-deeplinks
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes a local script
scripts/cursor-deeplink-gen.pyto facilitate link generation. This is a functional requirement to ensure proper URL encoding and length validation. - [DATA_EXFILTRATION] (SAFE): The instructions include a specific 'Safety + UX checks' section that mandates excluding secrets (API keys, tokens, passwords) from generated links.
- [REMOTE_CODE_EXECUTION] (SAFE): Although the skill generates links that can modify the project environment (e.g., creating files in
.cursor/rules/), it explicitly notes that these links do not auto-execute and require explicit user approval in the Cursor editor. - [PROMPT_INJECTION] (SAFE): No patterns of system prompt extraction or safety filter bypass were detected. The skill focuses on structured data formatting for tool integration.
Audit Metadata