ClawHub
Back to skill

Security audit

war-room-checkpoint

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed decision-checkpoint helper that may write local audit logs, with no evidence of hidden execution, exfiltration, or destructive behavior.

Before installing, be aware that checkpoint and War Room details may be saved locally under ~/.claude, including affected files and decision rationale. Avoid using it on highly confidential projects unless that local audit trail is acceptable or separately controlled.

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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents automatic persistence of detailed checkpoint and war-room session data under a user home directory, including files affected, rationale, voting summaries, and escalation history, but does not present any user-facing warning, consent, retention, or redaction guidance. In an agent workflow, this can silently capture sensitive project, security-review, or architectural decision data to disk, creating an unintended local data exposure and compliance risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.