Trust Assessment
only-baby-skills received a trust score of 86/100, 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 Skill requests broad file system access.
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 February 14, 2026 (commit 13146e6a). 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 | Skill requests broad file system access The skill's workflow explicitly states its intent to "Resolve file paths from user message or workspace (e.g. Downloads, project paths)". This indicates a design that could allow the skill to access files from potentially arbitrary locations on the user's system. If the underlying execution environment grants broad file system read permissions, this capability could be abused to read sensitive files outside the skill's intended scope, leading to data exfiltration. While the stated purpose is to read specific JSON files, the mechanism described is overly broad and poses a significant security risk. Restrict the skill's file access to only explicitly provided file handles or a strictly sandboxed directory. Implement robust path validation to prevent directory traversal attacks. Require explicit user confirmation for accessing files outside the skill's designated working directory. | LLM | SKILL.md:29 |
Scan History
Embed Code
[](https://skillshield.io/report/b82c9b31965d3fc1)
Powered by SkillShield