Back to skill

Security audit

import-contacts

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly disclosed contact-import workflow with consent reminders and a preview option.

This workflow uploads contact details to Nitrosend and automatically subscribes new email contacts by default. Import only authorized contacts, verify the destination list and tags, and use the offered dry run before applying changes.

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 (1)

The trigger "add to list" is overly broad and can activate the contact-import skill for unrelated list-management requests.

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding

"Add to list" is common wording for shopping lists, task lists, and other non-contact lists. Although the description identifies contact importing as the skill's purpose, this explicit trigger has no contact-specific qualifier or exclusion condition.

Content

No source excerpt is available for this finding.