ClawHub
Back to skill

Security audit

Daily Summary

Security checks for vulnerabilities and agentic risk

Overview

This skill creates a local daily summary with token usage, and its command use and file writing are disclosed and aligned with that purpose.

Before installing, be aware that using this skill will run `openclaw status --json` locally and create or update a dated summary file in your OpenClaw workspace memory directory. Check the generated summary if token usage or work-summary details are sensitive in your environment.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly writes or updates a file under the user's workspace, but the description does not clearly warn the user that local state will be modified. This can lead to unexpected persistence, overwriting existing notes, or silent accumulation of sensitive usage summaries without informed user consent.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The package description is written as a Chinese-only skill description, indicating the skill is intended to operate in Chinese without any mention of language choice or opt-in. This creates a natural-language locale policy concern because the skill appears to impose a specific language by default.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The skill runs a local command (`openclaw status --json`) to collect usage data, but this behavior is not surfaced as a clear warning to the user. Even though the command appears read-only, executing local commands can expose environment-specific data and expands the skill's trust boundary without adequate disclosure.

Static analysis

No suspicious patterns detected.