ClawHub

Task Decomposition

Security checks across malware telemetry and agentic risk

Overview

This is a planning-only skill that writes task plans and lessons to workspace files; its persistence can expose sensitive notes if users put them there, but the behavior is disclosed and purpose-aligned.

Safe to install for planning workflows. Treat the plans/ directory and patterns.md as persistent workspace notes: review them before sharing a repository, keep secrets and full connection strings out of plan text, and prefer secret managers or protected environment configuration for credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Context Leakage

High
Category
Data Exfiltration
Content
## Sub-agent Delegation

- One sub-agent per independent BRANCH, not per task
- Record session ID on the task line
- Don't poll in loops — check on events or when asked

## Progress Report
Confidence
83% confidence
Finding
Record session

Credential Access

High
Category
Privilege Escalation
Content
## Tasks

- [x] 1. (S) Provision database — Postgres 16, endpoint saved to .env
- [ ] 2. (M) Build auth middleware (depends: 1)
- [ ] 3. (M) Build CRUD endpoints (depends: 1)
      ↳ parallel with 2
Confidence
91% confidence
Finding
.env

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal