ClawHub
Back to skill

Security audit

Sui Auto Test

Security checks across malware telemetry and agentic risk

Overview

This is a local Sui Move coverage and test-generation helper, with the main caution that it tells the agent to commit test changes automatically.

Install this only if you want an agent to inspect and improve a local Sui Move project. Run it on a branch, review generated reports and test diffs, and do not allow git commits unless you explicitly ask for them after checking exactly what will be staged.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly instructs file reads, file writes, and shell execution, but it does not declare any permissions or boundaries for those capabilities. This is dangerous because an agent may execute commands and modify repository files without an explicit permission model, reducing transparency and increasing the chance of unintended or over-broad actions.

Tp4

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding
The documented behavior overstates what the skill does and omits meaningful operational details, including external command execution and repository modification steps. This mismatch is dangerous because users and agents may trust the description as a safe summary while the actual workflow causes broader side effects than advertised.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to run git add and git commit as a default step, which changes repository state and history beyond the core task of coverage analysis. This is dangerous because committing changes can persist unintended modifications, interfere with developer workflows, and create trust or supply-chain risks if done without explicit user approval.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The documentation tells the agent to write coverage and security report files without warning that these are repository modifications. This is dangerous because even seemingly harmless report generation can overwrite files, create noisy diffs, or leak sensitive analysis into tracked project artifacts without the user's awareness.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The commit instructions modify repository history without a user-facing warning or confirmation step. This is dangerous because users may not expect a coverage-analysis skill to create permanent VCS history entries, and such actions can accidentally publish incomplete, incorrect, or sensitive changes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.