Security Audit

Automattic/agent-skills:skills/wpds

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/wpds 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 Agent instructed to execute local lint scripts, posing command injection risk.

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	Agent instructed to execute local lint scripts, posing command injection risk The skill instructs the agent to 'use them [lint scripts] to validate the proposed code output when possible.' This implies the agent will execute local scripts. If the 'lint scripts' themselves or their arguments can be influenced by untrusted user input (e.g., the code to be validated, or the local context), this could lead to arbitrary command execution on the host system. This also implies the agent has permissions to execute local files, which is an excessive permission for an LLM agent. Avoid instructing the agent to directly execute local scripts. Instead, if validation is needed, provide a safe, sandboxed environment or a predefined, agent-controlled validation mechanism that does not involve direct command execution based on potentially untrusted input. If execution is unavoidable, ensure strict sanitization and sandboxing of all inputs and outputs, and limit the scope of executable commands.	LLM	SKILL.md:46

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/dac1051604677e4b.svg)](https://skillshield.io/report/dac1051604677e4b)