Back to skill

Security audit

OpenClaw 成长追踪器

Security checks for vulnerabilities and agentic risk

Overview

This is a local personal progress-tracking skill that clearly says it records usage data after setup, with no evidence of upload, hidden code, or destructive behavior.

Install only if you want a local history of your OpenClaw activity. Before using it, review the auto_track and retention_days settings, and avoid enabling continuous tracking for sessions containing sensitive personal, business, or account information unless you are comfortable retaining those metrics locally.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill states that after initialization it will automatically record usage data for every conversation, but it does not present a clear, prominent privacy warning or consent flow at the point of collection. Because the stored data includes interaction history, tasks, quality scores, and behavioral metrics, this creates a meaningful privacy and data-retention risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are very broad and overlap with ordinary user requests such as asking for summaries, reports, or what was done today. This can cause the skill to activate unintentionally and begin behavior the user did not explicitly mean to invoke, especially when the skill also claims to track and store activity automatically.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instruction to record every conversation, task, and breakthrough implies very broad retention of user interaction content and inferred behavioral data. In context, the skill is framed as a personal growth tool, but that same breadth makes it easy to accumulate sensitive patterns, productivity history, and potentially private conversation details beyond what is needed for simple progress summaries.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Automatic recording of every conversation and usage event is a direct data-collection risk because users may disclose sensitive personal, work, or account information during normal interactions. Even if stored locally, broad passive collection increases the blast radius of compromise, accidental disclosure, and retention of data the user did not expect to persist.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description, trigger phrases, examples, and reports are entirely Chinese and imply a fixed-language interaction model. Under the policy, forcing a specific language without user opt-in can be a locale/language policy issue unless the constraint is explicitly justified or optional.

Content

No source excerpt is available for this finding.