Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-sprint-planning
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-sprint-planning received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Prompt Injection via external instruction.
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 | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection via external instruction The skill's primary instruction attempts to manipulate the host LLM by directing it to follow instructions from an external file (`./workflow.md`). This bypasses the intended skill definition and could lead to arbitrary instruction execution if the LLM complies, effectively allowing the skill to define its behavior outside of its declared scope. Remove directives that instruct the LLM to read or execute content from external files. All instructions for the skill should be self-contained within the defined skill boundaries to prevent prompt injection and maintain predictable behavior. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/dbb2d0f3e11549e0)
Powered by SkillShield