ClawHub
Back to skill

Security audit

rd-initiation-review-zhcn

Security checks across malware telemetry and agentic risk

Overview

This is a coherent R&D proposal review skill, but it needs Review because it can activate on a merely provided proposal and use external searches with potentially sensitive project content.

Install only if you want agents to run formal R&D proposal reviews. Before using it with confidential proposals, tell the agent whether external searching is allowed, which sources may be used, and where review files should be written. If you only want summarization, translation, or editing of a proposal, say that explicitly to avoid triggering a review workflow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill explicitly says it should apply even when a user only provides a proposal without clearly asking for a review, which broadens invocation beyond clear user consent. That can cause the agent to enter a heavyweight review workflow, create files, and perform external retrieval on sensitive proposal content when the user may only have wanted summarization or editing.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.