Back to skill

Security audit

Smart Summarizer

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward summarization skill with no code execution or persistence, though users should avoid giving it sensitive or unauthorized content.

Before installing, treat this as a convenience summarizer: use it for public or authorized content, avoid secrets or regulated personal data, and be careful when pasting paywalled, private, or confidential material.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill encourages users to paste URLs, transcripts, emails, PDFs, and other long-form content but does not warn that these inputs may contain sensitive, personal, proprietary, or access-restricted information. This increases the risk that users will submit confidential data or external links without understanding the privacy, authorization, and data-handling implications.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill defines very generic trigger phrases such as 'Summarize:', 'Quick summary:', and 'Meeting notes:' that closely resemble normal user conversation. In agent environments that auto-route or invoke skills based on message content, these broad patterns can cause unintended activation on ordinary text, external URLs, or pasted content, which may lead to accidental processing of sensitive material or confusion about which tool is handling the request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.