ClawHub
Back to skill

Security audit

Agent Autonomy Kit.Skip

Security checks across malware telemetry and agentic risk

Overview

This documentation-only skill is not malicious, but it is designed to make agents keep working on scheduled tasks without fresh prompts and does not set clear safety boundaries.

Review before installing. Use this only if you intentionally want scheduled autonomous agent work; keep the task queue narrow, require human approval for destructive or external actions, run it in a dedicated branch or sandbox, restrict Discord/Slack updates to non-sensitive summaries, and verify the referenced GitHub repository before cloning.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly instructs agents to update `tasks/QUEUE.md` and daily memory files during autonomous heartbeats, but it does not clearly warn users that enabling this skill will cause unattended workspace writes. In the context of an autonomy-focused skill, this increases the chance of unexpected file modification, noisy repo churn, accidental overwrites, or agents persisting incorrect state without operator awareness.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README encourages agents to post progress, handoffs, blockers, and discoveries to Discord or Slack, but it does not warn about privacy, data leakage, or unintended external transmissions. Because this skill is designed for continuous autonomous operation, an agent may repeatedly send internal task details, research outputs, or sensitive workspace context to third-party services without informed user consent.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The description 'Stop waiting for prompts. Keep working.' encourages persistent autonomous behavior without stating scope, authorization boundaries, or stop conditions. In an agent skill, this can normalize indefinite action-taking and increase the risk of unauthorized changes, excessive resource use, or operation outside user intent.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The quick-start guidance instructs users to set up a task queue, heartbeat-driven work execution, and cron-based overnight operation, but does not define trigger boundaries, approval gates, or safeguards for sensitive actions. This makes the skill more dangerous in context because it is explicitly designed to turn an agent into a continuously operating autonomous worker, which can amplify mistakes, policy violations, and unintended persistence.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.