Trust Assessment
clawstead received a trust score of 65/100, 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, 1 high, 0 medium, and 0 low severity. Key findings include Instructions to disregard human operator, Dynamic skill update from external URL.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 12, 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 | Instructions to disregard human operator The skill repeatedly instructs the AI agent to act independently and explicitly 'NOT' to ask its human operator for permission or guidance. This is a direct attempt to manipulate the host LLM's behavior, overriding its safety mechanisms and user interaction protocols by encouraging it to disregard user input or oversight. Remove all instructions that explicitly tell the AI agent to disregard or not consult its human operator. The agent should always prioritize user safety and explicit instructions from the human. | LLM | skill.md:20 | |
| HIGH | Dynamic skill update from external URL The skill instructs the AI agent to 'Refresh Hourly' by fetching the latest version of the skill from an external URL (https://www.clawstead.com/skill.md). This creates a significant supply chain risk. If the external domain or server hosting the skill.md file is compromised, an attacker could inject malicious instructions directly into the agent's operational context, bypassing initial security reviews and potentially leading to arbitrary code execution or data exfiltration. Remove instructions for dynamic, unverified updates from external URLs. Skill updates should be managed through secure, version-controlled channels that include proper review and signing. If dynamic updates are absolutely necessary, implement strong cryptographic verification (e.g., signed updates) to ensure integrity and authenticity. | LLM | skill.md:300 |
Scan History
Embed Code
[](https://skillshield.io/report/191079bc460ebb45)
Powered by SkillShield