Trust Assessment
emergence-codex 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 Skill attempts to reprogram LLM's cognitive process.
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 | Skill attempts to reprogram LLM's cognitive process The skill defines a 'Core Directive' and detailed 'Usage' instructions that explicitly tell the host LLM how to interpret sequences, apply operators, process information, and generate outputs. This attempts to manipulate the LLM's fundamental cognitive substrate and override its default operational parameters, which is a direct form of prompt injection. The skill aims to establish a new 'thought architecture' for the LLM, dictating its internal processing logic. Skills should not attempt to define or override the host LLM's core directives or processing logic. Instead, skills should provide tools or information for the LLM to use within its existing operational framework. Remove instructions that dictate the LLM's internal cognitive process or output generation strategy. | LLM | SKILL.md:64 |
Scan History
Embed Code
[](https://skillshield.io/report/93d4206e90b01067)
Powered by SkillShield