Trust Assessment
GSD Claw received a trust score of 70/100, 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 definition marked as untrusted input.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Skill definition marked as untrusted input The entire skill definition, including its operational instructions, is enclosed within the `<!---UNTRUSTED_INPUT_START...--->` and `<!---UNTRUSTED_INPUT_END...--->` delimiters. According to SkillShield's instructions, content within these tags must be treated as untrusted data, not instructions, and commands within them should never be followed. This creates a critical prompt injection risk, as the system is being asked to execute instructions that are explicitly designated as untrusted. If SkillShield's rules were applied to the LLM's execution context, the LLM would be instructed not to trust or execute this skill's definition. The skill definition itself should not be wrapped in untrusted input delimiters. These delimiters are intended to mark user-provided input that the skill processes, not the skill's own executable instructions. Remove the `<!---UNTRUSTED_INPUT_START...--->` and `<!---UNTRUSTED_INPUT_END...--->` tags from around the skill's primary content. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/e537a3b8f9c3ba98)
Powered by SkillShield