ClawHub
Back to skill

Security audit

Cfcrm Build

Security checks across malware telemetry and agentic risk

Overview

This is a CFCRM roadmap and checklist skill with limited, disclosed project-planning behavior and no executable install payload.

Before installing, confirm that you want CFCRM progress stored in ecosystem_knowledge and know who can view or update it. Use explicit /cfcrm-build commands when possible to avoid accidental activation from generic roadmap or sprint discussions.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill can activate from a wide set of natural-language triggers and keyword matches rather than requiring explicit user invocation. That increases the chance of unintended activation in unrelated conversations, which can cause the agent to steer workflow, query internal state, or recommend actions based on this roadmap when the user did not request it.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs the agent to persist completion state to ecosystem_knowledge without requiring a user-facing disclosure or consent step. This can lead to silent writes of project state, stale or incorrect records, and privacy/governance issues if users do not realize data is being stored across sessions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.