Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-help
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-help 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 for arbitrary file reading via configurable paths.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential for arbitrary file reading via configurable paths The skill explicitly states its intention to read content from files. Specifically, it will read 'Files matching `outputs` patterns at resolved `output-location` paths' and from a path specified by `project_knowledge`. These `output-location` and `project_knowledge` variables are resolved from configuration files (`config.yaml` and `user-config.yaml`). If an attacker can manipulate these configuration files (e.g., by modifying `user-config.yaml` or through prompt injection that influences the LLM's interpretation of these variables), they could potentially set `output-location` or `project_knowledge` to arbitrary file paths on the system. This would allow the skill to read and potentially exfiltrate sensitive data from unintended locations, constituting a data exfiltration risk and an excessive permission. 1. **Path Sanitization**: Implement strict validation and sanitization for `output-location` and `project_knowledge` values to prevent directory traversal (e.g., `../`) and ensure paths are within an allowed, secure directory. 2. **Scope Restriction**: Limit the scope of file access to only necessary directories, ideally within the project's designated output or data folders, preventing access to arbitrary system paths. 3. **Pattern Validation**: Validate `outputs` patterns to ensure they are not overly broad or malicious, preventing unintended file matches. 4. **Input Validation**: If `user-config.yaml` or other configuration sources can be influenced by untrusted user input, implement robust input validation to prevent injection of malicious paths or patterns. 5. **Least Privilege**: Ensure the skill's execution environment operates with the minimum necessary file system permissions. | LLM | SKILL.md:32 |
Scan History
Embed Code
[](https://skillshield.io/report/f22ceab8b6895e4d)
Powered by SkillShield