Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-agent-quick-flow-solo-dev
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-agent-quick-flow-solo-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, 0 high, 1 medium, and 0 low severity. Key findings include Broad filesystem access and potential data exposure via project 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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Broad filesystem access and potential data exposure via project context loading The skill instructs the agent to search for `**/project-context.md` recursively across the filesystem and load its content as a foundational reference. This grants excessively broad read permissions, allowing the agent to access any file named `project-context.md` in any directory. If such a file contains sensitive information (e.g., credentials, proprietary data, internal configurations), loading it into the LLM's context creates a risk of data exfiltration through subsequent responses, logs, or unintended processing by the LLM. Restrict the search scope for `project-context.md` to a specific, well-defined project directory (e.g., `./project-context.md` or `.{project_root}/project-context.md`) rather than using a recursive wildcard (`**`). Implement content filtering or redaction for sensitive information within loaded files before they are processed by the LLM. Ensure the agent's execution environment has appropriate filesystem access controls to limit what files can be read. | LLM | SKILL.md:37 |
Scan History
Embed Code
[](https://skillshield.io/report/89e344031758f505)
Powered by SkillShield