ClawHub
Back to skill

Security audit

Daily Workflow

Security checks across malware telemetry and agentic risk

Overview

This skill is a project-local checkpoint and handoff note writer with disclosed, bounded persistence and no evidence of hidden or destructive behavior.

Install this if you want an agent to maintain lightweight project status and handoff notes. Review the generated Docs/ files before sharing them, because they may summarize project context, commands, blockers, and file paths, but the skill explicitly instructs the agent not to store credentials or sensitive records.

A.I.G

By Tencent
Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Content
## Archive Safety / 归档安全

Archiving older status history is allowed only by moving content into `Docs/archive/`. Never delete history automatically.

## Release Checklist / 发布检查
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.