Security Audit

Automattic/agent-skills:skills/wp-project-triage

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/wp-project-triage 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 Potential Credential Harvesting from wp-config.php.

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

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Credential Harvesting from wp-config.php The `detectConfigConstants` function explicitly targets and reads the `wp-config.php` file. This file is known to contain highly sensitive information, including database credentials (DB_USER, DB_PASSWORD), authentication unique keys and salts (AUTH_KEY, SECURE_AUTH_KEY, etc.), and potentially other API keys or secrets. Although the function's implementation is truncated in the provided snippet, the intent to extract 'config constants' from this file poses a significant risk of credential harvesting and data exfiltration if these sensitive values are included in the skill's JSON output. Review the full implementation of `detectConfigConstants` to ensure that no sensitive information (e.g., database credentials, authentication salts, API keys) is extracted, processed, or included in the skill's output. If certain constants are necessary for triage, ensure they are non-sensitive or are strictly redacted/masked before being reported.	LLM	scripts/detect_wp_project.mjs:190

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d28d565bbb663261.svg)](https://skillshield.io/report/d28d565bbb663261)