Security audit

L4 Skill Forge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent skill-building assistant with optional local scripts, and the main caution is that its broad trigger phrases may activate it for generic skill-related requests.

Install only if you want a skill-focused assistant for building or reviewing Agent Skills. Review the publisher, run the included Node scripts only in a workspace you intend to modify, and treat the score output as a checklist signal rather than a security certification.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The README advertises very generic activation phrases such as '帮我做一个 skill' and '对这个 skill 做安全审查', which are broad enough to overlap with ordinary user requests. In an auto-activation ecosystem, this can cause unintended invocation of the skill in contexts where the user did not explicitly choose it, creating prompt-routing confusion and potentially exposing unrelated content to the skill’s workflow.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The activation triggers are overly broad and match very common requests such as 'help me make a skill' or 'do a security review', which can cause unintended auto-activation in unrelated contexts. In a high-authority skill that guides file creation, evaluation, and release processes, accidental invocation can override more appropriate task handling and expand the skill's influence beyond the user's actual intent.

Static analysis

No suspicious patterns detected.