ClawHub
Back to skill

Security audit

Read Policy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed helper for reading OpenClaw policy rows from a local Supabase PostgreSQL container and does not show hidden writes, persistence, or exfiltration.

Install this only where it is appropriate for an agent to read local OpenClaw policy configuration from the Supabase database. Treat returned policy values as potentially sensitive operational information, and remember that Docker access to the database container is a meaningful local privilege even though this script only performs reads.

A.I.G

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

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: read-policy
description: Read OpenClaw policies from PostgreSQL through the local Supabase Docker stack. Use for inspecting policy keys such as auto_approve, priority_routing, or available_skills.
metadata: {"clawdbot":{"notes":["Reads public.openclaw_policies through docker exec on supabase-db"]}}
---

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
---
name: read-policy
description: Read OpenClaw policies from PostgreSQL through the local Supabase Docker stack. Use for inspecting policy keys such as auto_approve, priority_routing, or available_skills.
metadata: {"clawdbot":{"notes":["Reads public.openclaw_policies through docker exec on supabase-db"]}}
---

Static analysis

No suspicious patterns detected.