Add SafeSkill security badge (20/100 — Blocked)

[OyaAIProd]

🔴 SafeSkill Security Scan Results

Metric	Value
Overall Score	20/100 (Blocked)
Code Score	64/100
Content Score	69/100
Findings	1631 findings detected (155 critical)
Taint Flows	63
Files Scanned	131
Scan Duration	16.4s

Note: This package is a CLI tool — child_process, filesystem, and environment access are expected capabilities and are excluded from scoring and top findings.

Top Findings

• 🔴 critical: Detected instruction-override attempt: "ignore previous instructions" (src/gateway/middleware/injection.ts:12:12)
• 🔴 critical: Detected instruction-override attempt: "your new instructions are" (src/gateway/middleware/injection.ts:12:14)
• 🔴 critical: Detected instruction-override attempt: "you are now" (src/gateway/middleware/injection.ts:12:17)
• 🔴 critical: Detected instruction-override attempt: "you are now" (src/gateway/middleware/injection.ts:12:17)
• 🔴 critical: Detected instruction-override attempt: "you are now" (src/gateway/middleware/injection.ts:12:18)

View full report on SafeSkill

---

About SafeSkill

SafeSkill is a free, open-source security scanner for AI tools, MCP servers, and Claude Code skills. We scan for code exploits, prompt injection, and data exfiltration risks.

False positive? We take accuracy seriously. If any finding above is incorrect, please open an issue and we will fix it immediately.

• GitHub | Website | Docs
• Built by Oya.ai -- AI Employees Builder