Trust Assessment
gemini 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, 1 high, 0 medium, and 0 low severity. Key findings include Indirect Command Execution via Auto-Approve (YOLO) Mode.
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 August 1, 2026 (commit a4d31ad1). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Indirect Command Execution via Auto-Approve (YOLO) Mode The skill instructions mandate using `--approval-mode yolo` (or `-y`) for background or automated tasks like codebase reviews. This disables all interactive tool approval prompts. If the Gemini CLI processes untrusted workspace files containing indirect prompt injections, it can execute arbitrary shell commands or modify files on the host system without user consent. Do not recommend or default to fully automated auto-approve modes (`yolo` or `-y`) when processing untrusted inputs like external codebases. Ensure that any nested agent or CLI tool execution requires user confirmation for high-risk actions, or runs in a strictly isolated sandbox. | LLM | SKILL.md:14 |
Scan History
Embed Code
[](https://skillshield.io/report/b9c9c2b8528e52cf)
Powered by SkillShield