Back to skill

Security audit

Api Tester Dd7739

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown guide skill for API-testing/API-integration learning, with no code execution, persistence, credential handling, or hidden data access.

Safe to install as a reference guide. Be aware that the trigger "New" is overly broad and may activate the skill in unrelated conversations; tightening the trigger to API-testing-specific phrases would improve usability.

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger includes the very common term "New", which is likely to appear in many unrelated user requests and can cause accidental skill activation. In an agent environment, unintended invocation can redirect workflows, produce irrelevant actions, or expose users to behavior they did not explicitly request.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger scenarios are loosely defined, such as activating when the user says "New" or when they need related help, without clear scope boundaries. This ambiguity increases the chance of overmatching and unintended execution, especially because the skill concerns API usage and third-party platform integration that may influence external-facing tasks.

Content

No source excerpt is available for this finding.