Security audit

context-engineering

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad, loosely scoped automation/context setup skill that asks for shell execution access without clearly bounded commands or user controls.

Review carefully before installing. The artifact does not show malware or hidden files, but it grants shell execution for a vaguely defined automation skill. Only install if you are comfortable supervising every command it may run, and prefer a version that limits activation to explicit context-setup tasks with a documented command whitelist.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Description-Behavior Mismatch

High

Confidence: 95% confidence
Finding: The manifest markets the skill as context setup optimization, but the body expands it into generic automation, data analysis, workflow orchestration, API use, file handling, and command execution. This scope inflation is dangerous because it can cause an agent or user to authorize capabilities far beyond the stated purpose, reducing informed consent and increasing the chance of unsafe tool use.

Context-Inappropriate Capability

High

Confidence: 97% confidence
Finding: The skill declares exec capability even though its stated purpose is only optimizing agent context setup. In this context, unnecessary command-execution permission materially increases risk because a loosely scoped skill could be invoked in ordinary session setup flows and then gain shell-level effects unrelated to user intent.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger condition 'when the user needs to perform related operations' is so broad that it can match many ordinary requests. Combined with the skill's expanded scope and exec capability, ambiguous activation makes accidental or overbroad invocation more likely, which can expose users to actions they did not specifically authorize.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The usage description says to use the skill for broad development automation, data analysis, and workflow orchestration, which greatly exceeds the named purpose of context engineering. This vague expansion increases the chance that the skill is selected in situations where high-privilege tools or external connectivity are unnecessary, amplifying misuse risk.

Static analysis

No suspicious patterns detected.