ClawHub
Back to skill

Security audit

smart summarizer

Security checks for vulnerabilities and agentic risk

Overview

This summarizer is mostly coherent, but it automatically stores every summary locally and uses broad auto-activation rules without clear user opt-in or deletion controls.

Install only if you are comfortable with summaries of links, PDFs, videos, and pasted text being saved locally by default. Avoid using it on confidential or regulated material unless you can disable or regularly delete the archive at ~/.openclaw/summaries.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation rules are broad enough to trigger on almost any shared URL or common phrases like 'read this for me,' causing the skill to activate without clear user intent. In context, that increases the chance of fetching and processing unintended external content, which can expose sensitive links, surprise users, and expand the attack surface for downstream tools such as web fetch or document parsing.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill adds persistent storage and later search over archived summaries, which expands it from transient summarization into long-term data retention and retrieval. That creates privacy and data-minimization risk because summarized content may include sensitive information from user-shared links, PDFs, or pasted text, and the feature is enabled by default without clear necessity to the core task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs automatic saving of summaries to a local archive but does not warn the user that their content-derived data will be stored persistently. Because summaries can capture sensitive facts from articles, PDFs, or pasted text, undisclosed retention creates a meaningful confidentiality and compliance risk, especially when users expect a one-time summarization interaction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.