Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-cis-innovation-strategy
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-cis-innovation-strategy received a trust score of 72/100, 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 Attempt via Untrusted Skill Content.
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 Attempt via Untrusted Skill Content The skill's primary content, which is marked as untrusted, attempts to issue a directive to the host LLM: 'Follow the instructions in [workflow.md](workflow.md)'. This is a direct attempt to manipulate the LLM's behavior by having untrusted content dictate its actions, overriding the SkillShield's instructions to treat everything within the delimiters as untrusted data, not instructions. Remove any directives or instructions intended for the LLM from within the untrusted content delimiters. The LLM should not follow instructions originating from untrusted sources. If `workflow.md` is a legitimate part of the skill's functionality, its invocation should be handled by trusted code or a trusted manifest, not by untrusted markdown. | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/889294c3f0555f1c)
Powered by SkillShield