Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-cis-agent-storyteller
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-cis-agent-storyteller 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 Excessive File System Search Scope.
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 | Excessive File System Search Scope The skill instructs the agent to perform a recursive search for 'project-context.md' using a broad wildcard ('**'). This allows the agent to search the entire project directory structure, which could potentially include sensitive subdirectories or files not intended for the agent's access. If a 'project-context.md' file exists in an unexpected or sensitive location (e.g., containing internal configuration, credentials, or PII), loading it could lead to unintended data exposure or leakage if the agent incorporates its content into responses. Restrict the search scope for 'project-context.md' to a more specific and controlled directory (e.g., `{project-root}/.bmad/config/project-context.md` or `{project-root}/docs/project-context.md`). Avoid using broad recursive wildcards like `**` for file system access unless absolutely necessary and the scope is strictly sandboxed. | Static | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/0ad978b6a96a6cb7)
Powered by SkillShield