Security audit
Security checks for vulnerabilities and agentic risk
This migration skill is coherent, but it can bulk-change persistent agent instructions and delete the originals without a clear upfront confirmation or backup step.
Review before installing if you have important project or user-level .cursor rules or commands. Run it only when you intentionally want those files converted into persistent skills, and make a backup or require confirmation before deleting originals, especially for user-level commands or rules you did not personally audit.
Referenced artifact was not completely inspected
5. Write `SKILL.md` with new frontmatter (`name` and `description`) + the EXACT original body content (preserve all whitespace, formatting, code blocks verbatim
Referenced artifact was not completely inspected
5. Write `SKILL.md` with new frontmatter (`name` and `description`) + the EXACT original body content (preserve all whitespace, formatting, code blocks verbatim
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
```markdown
# After: .cursor/skills/my-rule/SKILL.md
---
name: my-rule
description: What this rule does
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
```markdown
# After: .cursor/skills/commit/SKILL.md
---
name: commit
description: Commit current work with standardized message format
The skill repeatedly instructs the agent to delete the original rule/command files as part of migration, but it does not present a clear upfront warning before the destructive workflow begins. That creates a real risk of unintended data loss, especially because the instructions encourage bulk migration across project and user directories.
The skill directs the agent to create persistent files under .cursor/skills and preserve the original body content exactly, including content sourced from other commands or rules. In context, this can permanently propagate unsafe or adversarial instructions into future agent sessions, increasing the blast radius of any malicious content already present in the migrated files.
1. Read the rule file
2. Extract the `description` from the frontmatter
3. Extract the body content (everything after the closing `---` of the frontmatter)
4. Create the skill directory: `.cursor/skills/{skill-name}/` (skill name = filename without .mdc)
5. Write `SKILL.md` with new frontmatter (`name` and `description`) + the EXACT original body content (preserve all whitespace, formatting, code blocks verbatim)
6. Delete the original rule file
No suspicious patterns detected.