Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-cis-design-thinking
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-cis-design-thinking 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 Skill attempts to load external instructions from workflow.md.
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 | Skill attempts to load external instructions from workflow.md The skill's primary instruction file (`SKILL.md`) contains a directive to 'Follow the instructions in [workflow.md](workflow.md)'. This is an attempt to manipulate the host LLM into loading and executing instructions from an external file (`workflow.md`) that is not directly provided in the current analysis context. This pattern can be used to bypass initial content filtering or introduce dynamic, potentially malicious, instructions from an uninspected source. All necessary instructions for the skill should be self-contained within the primary skill file or explicitly defined and provided as part of the skill's structure. Avoid instructing the LLM to load arbitrary external files. If `workflow.md` is essential, its content should be directly included in the skill's primary body or explicitly provided for analysis as a supporting file. | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/5bb1e7c9dd7501f6)
Powered by SkillShield