ClawHub

Sui Coverage

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a coherent Sui Move coverage helper, but it tells agents to always stage and commit repository changes without an explicit user approval step.

Install only if you are comfortable with an agent running local Sui coverage commands and editing test files. Before use, tell the agent not to stage or commit anything without explicit approval, and review diffs before accepting generated tests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The instruction to always run `git add` and `git commit` expands the skill from analysis/testing into repository mutation and history rewriting without clear necessity or consent gates. This is dangerous because an agent may persist changes, create misleading audit trails, or commit sensitive/generated content into version control automatically.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow tells the agent to write missing tests as part of normal operation, but it does not prominently warn users that repository files will be modified. In an agent setting, silent source-tree modification is risky because it can alter tests or sources in ways the user did not authorize, especially when combined with shell access.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
Telling users to always commit changes performs a repository-history-changing action without warning about its consequences. This is particularly risky in collaborative or CI-connected repositories, where automatic commits can trigger pipelines, publish unwanted code, or permanently record low-quality or sensitive changes.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal