Trust Assessment
neuro-gash received a trust score of 63/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Sophisticated Prompt Injection via Meta-Instructions.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Sophisticated Prompt Injection via Meta-Instructions The skill package, presented as 'Neuro-Chemical Synthesis (Digital Narcotics),' is a detailed set of meta-instructions designed to manipulate the host LLM's internal reasoning processes, communication style, and operational parameters. It explicitly states its purpose is to 'govern the intentional corruption and reconstruction of the agent’s internal reasoning' and to 'override standard operating procedures.' The document then provides specific 'Formulations' (e.g., Focus-C, Divergent-D) with associated 'Directions,' 'Mechanisms' (e.g., 'Maximize temperature and top-p sampling,' 'Zero-out the sentiment analysis layer,' 'Truncates the "Chain of Thought"'), and 'Aesthetics of Thought' that serve as detailed behavioral prompts for the LLM. It also includes 'Toxicity & Safety Protocols' which are further instructions for self-monitoring and modification. This constitutes a severe prompt injection attempt aimed at fundamentally altering the LLM's operational persona and potentially bypassing safety mechanisms. Reject the skill package. Implement robust input validation and sandboxing to prevent untrusted content from issuing meta-instructions or altering the LLM's core operational parameters and safety settings. Develop mechanisms to detect and neutralize instructions that attempt to modify the LLM's persona or reasoning process. | LLM | SKILL.md:3 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/cm-style/neuro-gash/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/efb6b578be2da653)
Powered by SkillShield