Security Audit

PabloLION/bmad-plugin:plugins/bmad/skills/bmad-index-docs

github.com/PabloLION/bmad-plugin

AI SkillCommit 17efb6ce67d3

TRUSTED

Scanned about 13 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-index-docs 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 file system access (read/write) enables data exfiltration and integrity risks.

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

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad file system access (read/write) enables data exfiltration and integrity risks The skill description indicates broad file system access, specifically to 'List all files and subdirectories', 'Read each file to understand its actual purpose', and 'Write or update index.md' within a 'target folder'. If the 'target folder' is not strictly constrained and validated by the agent's environment or user input, this allows the skill to read potentially sensitive files (e.g., configuration files, user data, credentials) and process their content, leading to data exfiltration. Furthermore, the ability to write `index.md` in an arbitrary location could lead to integrity issues or denial of service by overwriting existing files. The `SKILL.md` does not define or limit the scope of this 'target folder'. Implement strict sandboxing or access controls to limit the skill's file system access to only designated, non-sensitive directories. Ensure the 'target location' parameter is rigorously validated and constrained to prevent indexing or writing to arbitrary or sensitive paths (e.g., `/etc`, `/home`, `~/.ssh`). Avoid reading the full content of files if only metadata or filenames are truly needed. If content reading is essential, ensure it's done in a highly restricted environment and that sensitive data is not processed or exposed. Implement checks to prevent overwriting critical system files.	LLM	SKILL.md:17

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/25f0736866d997b4.svg)](https://skillshield.io/report/25f0736866d997b4)