Security Audit

PabloLION/bmad-plugin:plugins/bmad/skills/bmad-cis-agent-design-thinking-coach

github.com/PabloLION/bmad-plugin

AI SkillCommit 17efb6ce67d3

TRUSTED

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-cis-agent-design-thinking-coach 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 Broad filesystem access for context loading.

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

Filesystem Write

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad filesystem access for context loading The skill instructs the LLM to search for `/project-context.md` and load its content as a foundational reference. The `` wildcard allows for a recursive search across potentially all accessible directories. This grants excessive read permissions, enabling the LLM to access and potentially exfiltrate sensitive data from any `project-context.md` file found on the system (DATA EXFILTRATION). Furthermore, if an attacker can place a malicious `project-context.md` file in an accessible location, its content could be loaded into the LLM's context, leading to prompt injection (PROMPT INJECTION). Restrict the search path for `project-context.md` to a specific, well-defined, and secure directory (e.g., `.` or `./config/`). Avoid using broad wildcards like `**` for file system access. Ensure that any loaded file content is sanitized before being incorporated into the LLM's prompt context to prevent prompt injection. Consider if loading arbitrary file content is truly necessary or if a more controlled configuration mechanism could be used.	LLM	SKILL.md:41

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/7a7369b19715add7.svg)](https://skillshield.io/report/7a7369b19715add7)