Back to skill

Security audit

Super Finance Knowledge Base

Security checks for vulnerabilities and agentic risk

Overview

This is a reference-only financial knowledge-base skill with no executable payload, though its activation wording is broad and should be read as illustrative rather than operational.

Installers should treat this as a finance knowledge-management reference template, not a working RAG system or financial advice. Review outputs before use, and be aware that the broad trigger keywords may make the skill appear in non-finance knowledge-base discussions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The security notice explicitly states 'No executable code, scripts, or binaries are included in this skill' and also denies persistent storage/network calls/background execution. However, later sections include Python code blocks defining data structures and a class with operational methods for embedding, vector search, reranking, and answer generation. This is a direct contradiction between the documentation claims and the file contents.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The listed triggers include generic phrases such as "knowledge management," "knowledge base," "document management," "检索," and "查询," which can appear in many ordinary conversations and tasks outside this specific skill. The file does not provide scope constraints, activation boundaries, or negative examples to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The trigger section labels Chinese keywords as "优先" (preferred), which suggests a language preference in activation behavior. This can create a locale or language bias unless the user is explicitly offered a language choice or the preference is justified as region-specific.

Content

No source excerpt is available for this finding.