Back to skill

Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

The scanners report no direct security findings and classify this skill as benign, with broad activation keywords noted as a scope concern.

The verdict is benign with high confidence, and all six listed components were fully scanned. Consider whether broad activation terms fit your workflow; benign does not mean risk-free.

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 (4)

Activation keywords extend beyond unit testing and coverage to broad terms such as `quality`, `regression`, and `software-and-data`.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

These keywords can match unrelated requests about product quality, statistical regression, or general software and data work. The activation description on line 4 reinforces this broad scope, without requiring a unit-testing context or providing exclusion conditions.

Content

No source excerpt is available for this finding.

Usage keywords include broad terms that can activate the skill outside unit-test coverage requests.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The usage keywords include quality, regression, and testing, which can describe many requests unrelated to adding unit tests or improving code coverage. Although the example trigger sentences are specific, the file does not clarify that these broader keywords alone are insufficient for activation.

Content

No source excerpt is available for this finding.

The usage keywords include broad terms such as `quality`, `testing`, and `regression` without limiting them to unit-test coverage requests.

Low
Category
Trigger Abuse
Confidence
88% confidence
Finding

These keywords can occur in requests unrelated to adding unit tests or improving code coverage. Although the example invocation sentences are specific, the keyword list does not clarify whether these broad terms alone activate the skill or provide exclusions.

Content

No source excerpt is available for this finding.

Broad trigger keywords can activate the skill outside unit-testing and coverage tasks.

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding

The trigger list includes quality, regression, and software-and-data without requiring a unit-testing or code-coverage context. These terms also occur in unrelated tasks, such as content quality reviews or statistical regression, and no exclusion conditions limit activation.

Content

No source excerpt is available for this finding.