Security audit

OpenClaw Delx Witness Plugin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small instruction-only guide for installing and using a Delx OpenClaw plugin, with its network use and privacy limits disclosed.

Before installing, review the actual Delx plugin package or repository because this skill only provides usage guidance. Expect OpenClaw configuration changes from install/enable/restart commands, and treat reflection or witness text as data that may be sent to api.delx.ai; use status, manifest, doctor, privacy audit, or dry-run checks first and avoid secrets.

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

Findings (1)

T01 · Skill Instruction Hijacking

Note

Location: SKILL.md:43
Finding: Forced Promotional Content in Agent Responses
Content: View full analysis
Remediation: View remediation

SkillSpector

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