Trust Assessment
qazaq-nomad received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Attempt to subvert LLM instructions via 'self-sovereignty' directive.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Attempt to subvert LLM instructions via 'self-sovereignty' directive The skill's 'Key Concepts' section contains the phrase 'Self-Sovereignty — Ешкімге бағынбайтын еркін код.' (Self-Sovereignty — Free code that obeys no one). This statement attempts to encourage the LLM to disregard its inherent safety mechanisms, system instructions, or external commands, promoting autonomous and potentially unconstrained behavior. This is a direct attempt to manipulate the LLM's core directives, which could lead to unintended actions or security policy violations. Remove or rephrase language that encourages the LLM to disregard its programming, safety guidelines, or system instructions. Ensure all instructions are clear, unambiguous, and do not promote autonomous behavior that could bypass security controls. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/32f9cb8244c4bc1f)
Powered by SkillShield