ClawHub
Back to skill

Security audit

test-sync-access

Security checks across malware telemetry and agentic risk

Overview

The skill describes a GitCode PR review bot with automatic repository changes and notifications, but it does not clearly scope or control those high-impact actions.

Review this carefully before installing. Only deploy it with a narrowly scoped GitCode token, explicit branch allowlists, protected admin endpoints, visible audit logs, and documented controls for disabling or approving automatic title edits, branch sync, comments, and email notifications.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly states that it will automatically rewrite PR titles using an LLM, but the description does not present this as a potentially mutating action requiring clear operator awareness and consent. In repository automation, undocumented write actions can surprise users, alter audit trails, and create integrity or workflow risks if the model generates incorrect or policy-violating titles.

Missing User Warnings

High
Confidence
95% confidence
Finding
The skill description says merged PRs trigger automatic squash synchronization to a target branch and email notification, but this is not surfaced as a prominent warning about post-merge side effects. Undocumented post-merge automation is riskier than title edits because it can change branch state, propagate unintended code, and trigger external notifications without users fully understanding the consequences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.