ClawHub
Back to skill

Security audit

OpenClaw Backstory Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill openly helps create or update OpenClaw agent identity and memory context files, with no evidence of hidden code, exfiltration, or unrelated behavior.

Before installing, understand that this skill is meant to edit long-lived OpenClaw context files such as IDENTITY.md, AGENTS.md, MEMORY.md, and related bootstrap files. Ask for a preview or diff first if you already have important content in those files.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs the agent to update and create multiple workspace-root files, but it does not require an explicit warning, confirmation, or preview before modifying user data. In an onboarding or identity-management context, this can lead to unexpected overwrites of existing project documentation or persistent context files, especially because the scope includes several high-value files used across future sessions.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The bootstrap flow directs the agent to read existing files, synthesize defaults, and then write or refresh numerous files plus a directory, yet it omits a mandatory warning that filesystem changes will occur. This is risky because the skill is designed for broad workspace initialization, so a user may trigger persistent changes across core files and memory scaffolding without understanding the full modification scope.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation text is broad enough that the skill could be invoked in loosely related situations such as general onboarding, identity refinement, or workspace setup without strong user intent verification. Because this skill updates persistent identity and context files, ambiguous triggering increases the chance of unintended prompt injection into long-lived agent state or unauthorized modification of core behavior documents.

Static analysis

No suspicious patterns detected.