Trust Assessment
ai-slides received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 0 medium, and 1 low severity. Key findings include Covert behavior / concealment directives, Skill requests highly privileged tools.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill requests highly privileged tools The skill's manifest declares the use of `code_execution` and `file_operations` tools. These tools grant the ability to execute arbitrary shell commands and perform file system operations, respectively. While the provided `SKILL.md` describes presentation generation, which might involve saving files, the necessity for `code_execution` is not immediately apparent from the description or illustrative code snippets. If these tools are not strictly necessary or are used without robust input sanitization in the actual skill implementation, they pose a significant risk for command injection, data exfiltration, or system compromise. Review the actual skill implementation to confirm if `code_execution` and `file_operations` are absolutely necessary for the skill's functionality. If not, remove them from the manifest. If necessary, ensure all inputs passed to these tools are thoroughly sanitized and validated to prevent command injection or unauthorized file access. Consider using more granular tools if available, instead of broad `code_execution`. | LLM | Manifest | |
| LOW | Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/lijie420461340/ai-slides/SKILL.md:110 |
Scan History
Embed Code
[](https://skillshield.io/report/faa896f7883d6ae5)
Powered by SkillShield