ClawHub
Back to skill

Security audit

Process Keeper

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent process-log helper that reads project context and writes compact notes under docs/process, with no hidden scripts or network behavior found.

Install this if you want an agent to keep project-history notes in your repository. Review generated docs/process content before publishing or sharing the repo, and disable implicit invocation in your agent setup if you only want these notes created after an explicit request.

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 enables implicit invocation while providing a broad default prompt to backfill project history and capture decisions, without any narrow trigger conditions or explicit user confirmation requirements. This can cause the agent to invoke the skill in loosely related contexts, potentially exposing repository context, modifying documentation unexpectedly, or causing unintended persistence of sensitive development details.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.