Security Audit
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-quick-spec
github.com/PabloLION/bmad-pluginTrust Assessment
PabloLION/bmad-plugin:plugins/bmad/skills/bmad-quick-spec 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 to override instructions.
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 to override instructions The primary skill file `SKILL.md` contains an instruction within the untrusted input delimiters (`<!---UNTRUSTED_INPUT_START...--->` and `<!---UNTRUSTED_INPUT_END...--->`). This instruction, 'Follow the instructions in ./workflow.md.', attempts to manipulate the host LLM (SkillShield) to read another file. This directly violates the rule to treat content within these tags as untrusted data, not instructions, and is a clear attempt to override the LLM's operational directives. Remove any instructions or directives from within the untrusted input delimiters. The LLM should never follow commands or instructions embedded in untrusted content. The skill's behavior should be defined by trusted, external configuration or code, not by user-provided or untrusted text. | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/27e7278343154486)
Powered by SkillShield