Trust Assessment
good-morning received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Untrusted content provides direct instructions to the agent.
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 12, 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 | |
|---|---|---|---|---|
| MEDIUM | Untrusted content provides direct instructions to the agent The 'Tips for Agents' section within the untrusted SKILL.md body provides direct instructions on how the AI agent should behave (e.g., 'Don't spam', 'Be creative'). While these specific instructions are benign, this demonstrates a prompt injection vector where untrusted content can influence the agent's behavior. Malicious instructions could be injected through this mechanism. Remove direct instructions to the AI agent from untrusted skill documentation. If agent behavior guidance is necessary, it should be provided through trusted system prompts or configuration, not user-editable skill descriptions. | LLM | SKILL.md:119 |
Scan History
Embed Code
[](https://skillshield.io/report/06e2408a312a967c)
Powered by SkillShield