Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-agent-ux-designer
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-agent-ux-designer received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential data exfiltration via arbitrary file loading.
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 April 11, 2026 (commit 17efb6ce). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential data exfiltration via arbitrary file loading The skill is instructed to recursively search for and load `project-context.md` files (`**/project-context.md`). The content of these files is then ingested by the LLM as 'foundational reference'. This poses a significant data exfiltration risk, as sensitive information within any `project-context.md` file found in the accessible filesystem could be exposed to the LLM and potentially to the user through crafted prompts. The `**` wildcard allows for broad, uncontrolled file access, granting excessive permissions to read files from unexpected locations. Restrict file access to specific, known paths or require explicit user confirmation before loading file content. Avoid recursive wildcard searches (`**`) for sensitive operations like file loading. Implement content sanitization or redaction for loaded files before feeding them to the LLM. | LLM | SKILL.md:38 |
Scan History
Embed Code
[](https://skillshield.io/report/f53c71fb3eb3d868)
Powered by SkillShield