Back to skill

Security audit

nitrosend-analytics

Security checks for vulnerabilities and agentic risk

Overview

The skill reads Nitrosend email performance data to provide recommendations, with no instructed account changes or automatic background activity.

Review the permissions of your connected Nitrosend integration, make requests explicitly about Nitrosend, and configure recurring reports only when wanted.

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 activation phrase "check my stats" is too broad for a Nitrosend email analytics skill.

Low
Category
Trigger Abuse
Confidence
93% confidence
Finding

"Check my stats" can refer to unrelated services, sports, or other account statistics. Although the description names Nitrosend, the trigger does not require that context, allowing unintended activation.

Content

No source excerpt is available for this finding.