Back to skill

Security audit

What did I actually do? Claims vs record

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned local verification aid, but it depends on installing and enabling a local plugin that users should understand before use.

Before installing, understand that this skill depends on the ClawPhylax plugin and may read OpenClaw transcripts and local tool-outcome ledgers to verify claims. Install it only if you are comfortable enabling that local plugin and having the agent use session records for reconciliation.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs the agent or user to install and enable a plugin, which modifies the local environment, but it does not present that as a clear environment-changing action with explicit consent boundaries. Even though the text says the plugin is local and observe-only, automatic installation/enabling can still alter system state and expand the trusted computing base without sufficiently prominent warning.

Content

No source excerpt is available for this finding.