Back to skill

Security audit

Email Writer Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple email drafting helper with minor routing and language caveats, and no evidence of unsafe actions.

Safe to install for drafting email text. Be aware it may activate for generic email-writing requests, and specify the desired language, recipient details, and any facts that must be accurate.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough that the skill may activate for generic requests like 'write email' or 'email reply' even when the user did not intend to invoke this specific skill. This can cause unintended routing or overshadow more appropriate skills, though the skill itself is low-risk because it only drafts email content and does not send messages or access sensitive systems.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The use-case text includes 'English email,' which can bias the skill toward English-language output without an explicit user preference. This may produce responses in the wrong language or reduce user control, but in this context the impact is limited because the skill is a content-generation assistant and not connected to authentication, data handling, or external actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.