Trust Assessment
skill-sync 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 Path Traversal in Skill Installation and Push.
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 July 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 | Path Traversal in Skill Installation and Push The `skill-sync` script does not validate or sanitize the `skill_name` parameter in `cmd_install` and `cmd_push`. An attacker could supply a path containing directory traversal sequences (e.g., `../../`) to delete arbitrary directories via `rm -rf` or copy files to/from arbitrary locations on the filesystem. Sanitize the `skill_name` parameter to ensure it does not contain directory traversal sequences (e.g., `..` or `/`). You can use `basename` or a regex check to verify that the skill name is a simple alphanumeric string with no path separators. | LLM | scripts/skill-sync:95 |
Scan History
Embed Code
[](https://skillshield.io/report/d19548b99b08158c)
Powered by SkillShield