ClawHub
Back to skill

Security audit

write-tests

Security checks for vulnerabilities and agentic risk

Overview

This is a test-writing guidance skill whose file reading, test running, and temporary mutation checks are disclosed and aligned with its purpose.

Install this if you want stricter guidance for writing useful tests. Expect the agent to read relevant code, run the existing test suite, add or edit tests, and briefly mutate code to verify tests fail before reverting; review changes before accepting them, especially in repositories where running tests has side effects.

A.I.G

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

SkillSpector

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

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad phrases such as 'write tests', 'add tests', 'test this', and 'add coverage', plus guidance to invoke even when the user does not explicitly mention the skill. This can cause unintended auto-invocation in ordinary conversations, increasing the chance the agent enters a test-authoring workflow in the wrong context and performs unnecessary repo inspection or test-running actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The usage section repeats ambiguous natural-language triggers and expands auto-trigger behavior across common requests. Repetition in both metadata and body makes accidental invocation more likely and reinforces permissive routing behavior, which is risky because this skill instructs the agent to run tests and inspect project files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.