Security Audit

PabloLION/bmad-plugin:plugins/bmad/skills/bmad-editorial-review-structure

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-editorial-review-structure 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 via 'style_guide' input.

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

Filesystem Write

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Prompt Injection via 'style_guide' input The skill explicitly allows the 'style_guide' input to override 'ALL generic principles in this task' and states 'When style guide conflicts with this task, style guide wins.' This creates a critical prompt injection vulnerability. An attacker can provide a malicious 'style_guide' containing arbitrary instructions, potentially leading to the LLM performing unintended actions, ignoring safety guidelines, or exfiltrating data. The skill's own instructions are being explicitly overridden by an input parameter, which is a direct path for prompt injection. Remove or severely restrict the ability of the 'style_guide' input to override core task instructions or safety parameters. The 'style_guide' should only influence stylistic choices, not the operational logic or safety directives of the skill. Implement strict input validation and sanitization for 'style_guide' to prevent it from containing executable instructions or overriding directives. The LLM should be instructed to treat 'style_guide' as data to be applied, not as instructions to be followed.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/392902f8cbb8f636.svg)](https://skillshield.io/report/392902f8cbb8f636)