Safety Grades
Independent assessments of maintainer, permissions, supply chain, transparency, and incident history.
A+
17
B
1
| Grade | Item | Type | Score |
|---|---|---|---|
| A+ | brand-guidelines | Skill | 94 |
| A+ | canvas-design | Skill | 94 |
| A+ | webapp-testing | Skill | 94 |
| A+ | claude-api-skill | Skill | 94 |
| A+ | doc-coauthoring | Skill | 94 |
| A+ | internal-comms | Skill | 94 |
| A+ | theme-factory | Skill | 94 |
| A+ | algorithmic-art | Skill | 94 |
| A+ | web-artifacts-builder | Skill | 94 |
| A+ | frontend-design | Skill | 94 |
| A+ | word | Skill | 94 |
| A+ | skill-creator | Skill | 94 |
| A+ | excel | Skill | 93 |
| A+ | Skill | 93 | |
| A+ | slack-gif-creator | Skill | 93 |
| A+ | powerpoint | Skill | 93 |
| A+ | mcp-builder | Skill | 93 |
| B | hyperframes | Skill | 72 |
What the grades mean
- A+ / A: Official vendor or well-maintained, scoped permissions, clean record. Safe defaults.
- B: Sensible community pick. Review the install and permissions before granting sensitive access.
- C: Usable but comes with caveats. Read the red flags.
- D: Meaningful concerns. Only use in sandboxed or low-stakes contexts.
- F: Avoid unless you know exactly what you're doing and have mitigations.
Grades are advisory. They update as the ecosystem changes. They do not replace your own review of the code and permissions before granting an agent access to sensitive systems.