Security Audit

skill-sync

github.com/jdrhyne/agent-skills

AI SkillCommit a4d31ad11998

CAUTION

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

skill-sync received a trust score of 66/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Path Traversal in Skill Installation, Unverified Remote Code Execution via Unpinned Repository Sync.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, indicating areas for improvement.

Last analyzed on August 1, 2026 (commit a4d31ad1). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

63%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

2 findings

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	Path Traversal in Skill Installation The `skill-sync` script does not sanitize or validate the `skill_name` parameter in the `install` command. An attacker can supply a path traversal payload (e.g., `../../../../`) which resolves to directories outside the intended local skills directory. This leads to arbitrary directory deletion via `rm -rf "$dest"` and arbitrary file copy/overwrite via `cp -r "$src" "$dest"`. Sanitize the `skill_name` parameter to ensure it does not contain path traversal sequences like `..` or `/`. You can use `basename` or a regex check to validate that the skill name only contains alphanumeric characters, hyphens, and underscores.	LLM	scripts/skill-sync:101
MEDIUM	Unverified Remote Code Execution via Unpinned Repository Sync The `skill-sync` script pulls and installs executable scripts directly from the main branch of a remote GitHub repository (`https://github.com/jdrhyne/agent-skills.git`) without any commit pinning, cryptographic signature verification, or checksum validation. If the remote repository is compromised, malicious updates will be automatically pulled and executed on the user's system. Pin the repository to a specific, verified commit hash instead of pulling directly from the moving `main` branch, or implement signature verification for downloaded skills.	LLM	scripts/skill-sync:29

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d19548b99b08158c.svg)](https://skillshield.io/report/d19548b99b08158c)