Back to skill

Security audit

Trade Dashboard

Security checks for vulnerabilities and agentic risk

Overview

The skill is not clearly malicious, but it describes automatic feedback that can change other trade skills without explaining scope, approval, or rollback.

Review this skill before installing if you do not want an analytics dashboard to influence other trade skills. Require explicit approval before any feedback changes trade-hunter search behavior or trade-qualifier scoring weights, and verify what data is reused or retained.

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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is written entirely in Chinese, including the title, feature descriptions, and related skill labels, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific context. Under the policy for natural-language violations, a skill that effectively forces a specific language without opt-in should be flagged.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description text is presented in Chinese, and the rest of the document also assumes Chinese-language usage. Because no language choice, opt-in, or justification for a Chinese-only experience is provided, this may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises a self-evolving data feedback mechanism but does not explain what data is fed back, where it goes, or how it affects downstream systems. Automatic feedback loops can propagate incorrect, sensitive, or manipulated data into other skills, creating integrity, privacy, and unexpected automation risks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are broad enough to match many generic analytics requests, which can cause the skill to activate outside its intended scope. In a multi-skill environment, ambiguous invocation increases the chance of inappropriate data access, confusing handoffs, or use of this dashboard workflow when the user did not intend cross-skill analysis.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The statement that dashboard analysis automatically optimizes other skills describes an undocumented cross-skill side effect. This is dangerous because one skill's outputs may silently alter search strategies or scoring weights elsewhere, enabling error amplification, data poisoning, or unauthorized behavioral changes across the workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This file presents dashboard content partly in English and partly in Chinese, but it does not explain whether the locale is user-selected or intentionally region-specific. Under the language/locale policy, hard-coded mixed-language output can be a policy concern when no opt-in or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language metadata uses Chinese-only description and tags (for example, the description at L04 and tags at L17) without indicating that the skill supports other languages or that Chinese is an intentional, documented locale restriction. This can violate language/locale policy when a skill implicitly forces a specific language for discovery or use without user choice.

Content

No source excerpt is available for this finding.