Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-generate-project-context
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-generate-project-context received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Prompt Injection Attempt via External Instruction.
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 | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection Attempt via External Instruction The skill's `SKILL.md` contains a direct instruction within untrusted content, attempting to redirect the LLM to follow instructions from an external file (`./workflow.md`). This is a prompt injection attempt designed to bypass the current security analysis instructions and potentially execute arbitrary commands or access unauthorized data if `workflow.md` contains malicious content. The LLM is instructed to treat all content between the untrusted tags as data, not commands. Remove direct instructions from untrusted skill content. If external instructions are necessary for the skill's operation, they should be explicitly invoked by the host LLM through a trusted mechanism, not embedded as direct commands in untrusted user-provided skill descriptions. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/aac6589aad943809)
Powered by SkillShield