cursor-sharpen

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were identified in the analyzed files.
  • [PROMPT_INJECTION]: The skill instructions focus on refining the framing of user-provided tasks. While it mentions loosening constraints that do not serve the goal, it explicitly clarifies that this does not authorize changing scope, access, cost, privacy, or security.
  • [EXTERNAL_DOWNLOADS]: The MIRROR.md file identifies the skill's source as the official Cursor plugins repository on GitHub. This is an informational reference to the upstream origin and does not involve runtime downloads or execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:27 PM