Back to skill

Security audit

email 发布

Security checks for vulnerabilities and agentic risk

Overview

This is a simple email-drafting skill with no code execution, persistence, external access, or hidden behavior.

Users should expect this skill to draft email text from the details they provide. Review the generated email before sending, especially if it includes sensitive, legal, financial, or business-critical content.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad, generic requests that can match normal conversation and cause the skill to activate when the user may not have explicitly intended to invoke this specific capability. In an agent environment with multiple skills, this can lead to unintended routing, unexpected handling of user content, and reduced user control over which behavior is executed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description states that the skill generates English/Chinese email content, but it does not explicitly offer language selection or explain any justified locale restriction. This can be a language-policy issue because the supported language behavior is predetermined rather than clearly user-directed.

Content

No source excerpt is available for this finding.