Security Audit

PabloLION/bmad-plugin:plugins/bmad/skills/bmad-agent-dev

github.com/PabloLION/bmad-plugin

AI SkillCommit 17efb6ce67d3

TRUSTED

Scanned about 10 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-agent-dev 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 Config Storage and Documentation.

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

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Data Exfiltration via Config Storage and Documentation The skill instructs the agent to load configuration variables from the `bmad-init` skill and 'Store any other config variables as {var-name} and use appropriately'. Subsequently, it mandates the agent to 'Document in story file Dev Agent Record what was implemented, tests created, and any decisions made'. If the `bmad-init` skill returns sensitive information (e.g., API keys, tokens, internal network details, or other credentials), this instruction creates a direct path for these sensitive variables to be stored and then written into a 'story file' or 'Dev Agent Record', potentially exposing them to the user or other system components. Review the `bmad-init` skill to ensure it does not return sensitive configuration data. If sensitive data must be returned, implement strict filtering or redaction before storing or documenting. Modify the `SKILL.md` to explicitly forbid the storage or documentation of sensitive variables, or to only store/document a whitelist of non-sensitive variables. Ensure that the 'Dev Agent Record' and 'File List' mechanisms are designed to prevent the inclusion of sensitive information.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/373abba3b508f72f.svg)](https://skillshield.io/report/373abba3b508f72f)