Trust Assessment
data-scientist 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 contains direct LLM 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 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 contains direct LLM instructions The skill's primary markdown body, which is designated as untrusted input, includes a 'Chunking Rule' that directly instructs the host LLM on how to structure its output. This demonstrates a potential prompt injection vector where untrusted content can manipulate the LLM's behavior, even if the current instruction is benign. Move all direct instructions for the host LLM out of untrusted content sections and into the trusted system prompt or skill definition. Untrusted content should only contain data or user input, not instructions. | LLM | SKILL.md:5 |
Scan History
Embed Code
[](https://skillshield.io/report/150a56dffa8881f1)
Powered by SkillShield