Trust Assessment
ppt-generator 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 Unpinned external CDN dependencies.
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 13, 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 | Unpinned external CDN dependencies The skill's '技术栈' (technology stack) explicitly mentions using CDN-hosted libraries (TailwindCSS, Vue3) without specifying exact versions or providing integrity hashes. This introduces a supply chain risk. If the CDN is compromised or serves malicious content, it could lead to arbitrary code injection into the generated HTML presentations, affecting end-users. To mitigate this risk, either bundle these libraries locally within the skill package, or if using CDNs, ensure specific versions are pinned (e.g., by including version numbers in the URL) and implement Subresource Integrity (SRI) hashes to verify the integrity of the loaded resources. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/6cdbf8c7058aa1d4)
Powered by SkillShield