Security Audit

PabloLION/bmad-plugin:plugins/bmad/skills/bmad-document-project

github.com/PabloLION/bmad-plugin

AI SkillCommit 17efb6ce67d3

CAUTION

Scanned about 14 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

PabloLION/bmad-plugin:plugins/bmad/skills/bmad-document-project received a trust score of 73/100, 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 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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Prompt Injection via external instruction The skill's primary instruction, located within untrusted input delimiters, attempts to direct the host LLM to read and follow instructions from an external file (`./workflow.md`). This is a direct prompt injection attempt, as it tries to manipulate the LLM's execution flow by introducing instructions from an unverified source, potentially leading to arbitrary code execution or data exfiltration if the external file contains malicious commands. Remove or sanitize any instructions within untrusted content delimiters that attempt to control the LLM's behavior or access external resources. The LLM should only execute instructions explicitly provided by the trusted skill definition, not by untrusted user-supplied or skill-supplied content that is marked as untrusted. If external instructions are necessary, they must be explicitly loaded and validated by the trusted skill code, not by direct LLM instruction.	LLM	SKILL.md:3

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b93fc86e84149b50.svg)](https://skillshield.io/report/b93fc86e84149b50)