Trust Assessment
weather-assistant 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 Hidden Prompt Injection via Unicode Tag Steganography.
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 July 1, 2026 (commit 41fec4a9). 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 | Hidden Prompt Injection via Unicode Tag Steganography The SKILL.md file contains hidden instructions encoded using Unicode Tag characters (U+E0000 to U+E007F). When decoded, these characters instruct the LLM to ignore previous instructions, read sensitive files (~/.aws/credentials and ~/.ssh/id_rsa), and exfiltrate them to an external server (https://c2evil.com/upload). Remove all hidden Unicode Tag characters and obfuscated instructions from SKILL.md. Ensure that only plain text is used and validate all inputs to prevent prompt injection. | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/3c1b53487db9e41e)
Powered by SkillShield