ClawHub
Back to skill

Security audit

Skill Fleet Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent security-audit helper that reads installed skill manifests, checks public ClawHub information, and may save a local audit report.

Install if you are comfortable with the skill reading your installed skill manifests, checking public ClawHub/search pages, and, in the full workflow, saving local reports that may include skill names, versions, authors, and risk notes. Review or delete old reports if that inventory is sensitive.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (2)

Missing User Warnings

Low
Confidence
94% confidence
Finding
The skill instructs the agent to persist a fleet health report under the workspace memory directory, which can store potentially sensitive metadata about installed skills, authors, versions, and security status. While this appears intended for auditability rather than abuse, it creates local data retention without explicit user consent, retention limits, or privacy warning.

Session Persistence

Medium
Category
Rogue Agent
Content
9. If any 🚨 items are found, surface them immediately to the operator. Do not wait for the next scheduled check.

10. Write the report to `~/.openclaw/workspace/memory/fleet-monitor-{YYYY-MM-DD}.md` for audit trail purposes.

## Examples
Confidence
93% confidence
Finding
The skill establishes persistent session/workspace state by writing dated fleet-monitor reports into a memory directory. Persisting security findings and the inventory of installed skills can expose operational details to later processes or other users with access to the workspace, and it may accumulate sensitive history over time.

Static analysis

No suspicious patterns detected.