Back to skill

Security audit

Rust避坑指南

Security checks for vulnerabilities and agentic risk

Overview

This Rust guide has no executable payload, but it asks for broad read/execute/write authority and includes unrelated automation/API-key language that users should review before installing.

Install only if you are comfortable with a Rust guidance skill that may request command execution and file-writing authority. Prefer a revised version that narrows activation to Rust-specific questions and clearly limits any commands or edits to user-approved Rust project work.

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is presented as a Rust reference/education guide, but its manifest grants read, exec, and write capabilities that are far broader than necessary for that role. This creates a capability-to-purpose mismatch that could let the skill execute commands or modify files under the guise of benign programming help, increasing the chance of abuse or unexpected side effects.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The documentation says the skill's core capabilities are Chinese interaction and workflow automation, which conflicts with the rest of the file describing a Rust pitfall guide. Such inconsistency undermines user understanding and can conceal the real behavior or intended invocation conditions of the skill.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The performance and troubleshooting sections describe API calls, file parsing, command execution, and batch processing that do not match a narrowly scoped Rust coding guide. This mismatch can normalize unexpected network, file, or execution behaviors and make dangerous capabilities seem legitimate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The invocation description uses broad triggers like code generation, programming assistance, debugging, and deployment, which overlap with many ordinary development requests. Overbroad routing conditions can cause the skill to activate in situations beyond its advertised Rust-pitfall scope, exposing unnecessary privileged tools or steering users into unintended workflows.

Content

No source excerpt is available for this finding.