ClawHub
Back to skill

Security audit

rust-free

Security checks for vulnerabilities and agentic risk

Overview

This Rust helper is mostly documentation, but it asks for broad read, write, and command execution authority with vague API and file-handling claims that are not clearly scoped.

Review this before installing if you only want a Rust reference guide. It may be reasonable for an agent that reads Rust code, runs cargo commands, and applies fixes, but use it only in a trusted project/workspace and approve file writes or shell commands explicitly.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Confidence
97% confidence
Finding
The skill is presented as a Rust learning and code-review guide, but later advertises broad file handling, API integration, and command execution capabilities. That mismatch increases the chance that users invoke powerful actions they did not reasonably expect, enabling overprivileged behavior and abuse of agent tools beyond the stated educational purpose.

Context-Inappropriate Capability

High
Confidence
98% confidence
Finding
Granting exec to a Rust pitfall guidance skill is unjustified by the core use case and materially expands the attack surface. If the skill processes adversarial project content or user input, command execution could be steered into running local commands, inspecting the environment, or modifying the system in ways users would not expect from a documentation-oriented helper.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Advertising writing, external API access, and command execution without prominent user-facing warnings reduces informed consent and makes risky side effects easier to trigger. In the context of an educational Rust skill, these operations are out of scope and therefore more dangerous because users are less likely to anticipate data exfiltration, filesystem changes, or process execution.

Static analysis

No suspicious patterns detected.