Security Audit

Automattic/agent-skills:skills/wordpress-router

github.com/Automattic/agent-skills

AI SkillCommit 48d4aa21d0da

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

Automattic/agent-skills:skills/wordpress-router 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 Execution of unverified Node.js script in untrusted repository.

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 1, 2026 (commit 48d4aa21). 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

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Execution of unverified Node.js script in untrusted repository The skill explicitly instructs the agent to execute a Node.js script (`node skills/wp-project-triage/scripts/detect_wp_project.mjs`) within the 'Repo root' (current working directory). The 'Repo root' is an untrusted input provided by the user. The source code for `detect_wp_project.mjs` is not provided within this analysis context, meaning its security posture is unknown. Running an unverified script in an untrusted environment creates a significant command injection vulnerability. A malicious repository could potentially manipulate the script's execution environment, provide specially crafted files that exploit vulnerabilities within the script, or influence its behavior to achieve arbitrary code execution, data exfiltration, or other malicious actions. The script's stated purpose of 'detecting WP project' implies it will read and process files from the untrusted repository, granting it broad filesystem access (excessive permissions) to potentially sensitive data. 1. Provide the source code for `skills/wp-project-triage/scripts/detect_wp_project.mjs` for thorough security review and analysis. 2. Isolate script execution: Run the script in a strictly sandboxed environment with minimal necessary permissions and restricted network access. 3. Validate inputs: Ensure the script robustly validates all inputs, especially file paths and content read from the untrusted repository, to prevent path traversal, command injection, or other file-based attacks. 4. Avoid direct execution of unverified scripts: If possible, consider rewriting the project detection logic directly within the agent's trusted environment or using a more controlled and secure mechanism for interacting with untrusted file systems.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e613b6310baa5ac4.svg)](https://skillshield.io/report/e613b6310baa5ac4)