Back to skill

Security audit

Adversarial Verification

Security checks for vulnerabilities and agentic risk

Overview

This adversarial testing skill is purpose-aligned, but its verifier can run target-controlled commands on the host without enforcing the sandboxing it promises.

Install only if you will run it in a disposable, credential-free sandbox. Avoid using it on untrusted repositories or production paths until command execution is isolated and the CLI filename handling is fixed.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/simple-verify.js:50
Finding

Shell Command Injection Through a User-Controlled CLI Filename

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Error
Location
scripts/simple-verify.js:84
Finding

Untrusted npm Lifecycle and Build Scripts Execute Without Isolation

Content
View full analysis
Remediation
View remediation
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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document presents all operational guidance in Chinese and uses mandatory language throughout, but it does not state that the skill is region-specific or provide any user opt-in for language preference. This can violate language/locale policy expectations when skills should not force a specific language without user choice or a documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger conditions are overly broad ('high-risk changes', 'core functionality', 'security-related code', or 'user-requested verification') and can cause the skill to run in many unintended contexts. Because this skill explicitly promotes destructive/adversarial testing and real command execution, ambiguous invocation increases the chance of unnecessary risky actions, resource consumption, or disruptive validation outside appropriately scoped environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing instructions exclusively in Chinese, including installation, usage, and operational guidance. Under the language/locale policy, forcing a specific language without user opt-in or a documented regional constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JavaScript file uses Chinese for the top-level description, comments, and CLI output such as usage/help text, but provides no opt-in, language selection, or justification that the skill is intended only for a Chinese-speaking audience. That creates a natural-language locale policy issue because the skill effectively enforces a specific language for all users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language description is entirely in Chinese and does not indicate that other languages are supported or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a locale/language policy concern.

Content

No source excerpt is available for this finding.