Back to skill

Security audit

send-transactional

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly described, proportionate workflow for sending transactional messages through Nitrosend.

Nitrosend receives recipient details, message content and personalization, including any verification codes. Open/click tracking stays enabled. Use the offered dry run, verify the recipient and content before live delivery, and keep API keys in backend secret storage.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The sending workflow lacks a privacy warning that recipient details and message contents are transmitted to Nitrosend.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill instructs the agent to send recipient addresses and message contents through Nitrosend, including verification codes in the examples at lines 80–85. Although it offers a dry run and identifies the service, it does not warn users that personal data and potentially sensitive authentication content will be transmitted to a third-party provider.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

API Integration

text
POST https://api.nitrosend.com/v1/my/messages
Authorization: Bearer nskey_live_...
Idempotency-Key: verification-user-123-attempt-1
Content-Type: application/json