ClawHub
Back to skill

Security audit

Extracts durable workflow preferences and project conventions from a session, then proposes the smallest valid update to global or project CLAUDE.md files. Trigger when the user asks to remember rules, when repeated preference patterns appear, or at session end for non-trivial sessions.

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed session-learning skill that proposes small CLAUDE.md rule updates, with no bundled code or network behavior found.

Install this only if you want an agent to review sessions for durable preferences and propose persistent CLAUDE.md rules. Review each proposed rule and target file before approving writes, and be cautious about enabling automatic session-end writes.

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 manifest description uses broad triggers like remembering rules, repeated preference patterns, or session end for non-trivial sessions, which can activate on ordinary conversation without a sharply defined boundary. In a persistence-oriented skill, overbroad activation increases the chance that incidental user remarks are interpreted as durable instructions and proposed for storage in long-lived context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.