ClawHub
Back to skill

Security audit

Npv

Security checks for vulnerabilities and agentic risk

Overview

This skill is a harmless-looking local reference script, but its NPV financial guidance is materially generic and missing core NPV content users would expect.

Review this skill before relying on it for finance work. It does not appear to perform unsafe system actions, but its NPV reference content is incomplete and potentially misleading, so users should not treat it as authoritative for investment appraisal or financial decisions without independent verification.

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
  • 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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The skill advertises itself as a focused NPV reference tool, but the exposed commands and descriptions are mostly generic finance topics such as regulations, risks, instruments, and strategies. This mismatch can cause users or downstream agents to invoke the skill in contexts expecting precise NPV guidance and instead receive broad or irrelevant financial content, increasing the chance of erroneous decisions or inappropriate automation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation guidance is broad enough to trigger on ordinary finance discussions, not just clear NPV-related tasks. In agentic environments, overly permissive triggering can route unrelated requests to this skill, causing irrelevant outputs, context pollution, and incorrect task handling when users need specialized or different financial analysis.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script advertises itself as an NPV reference tool, but almost all output is generic finance and operations boilerplate rather than guidance on net present value. This can mislead users or downstream agents into trusting incorrect domain coverage, causing bad financial decisions or propagation of inaccurate information in automated workflows.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The formulas section is labeled as NPV formulas, but it omits the core NPV formula and instead presents unrelated metrics such as ROI, CAGR, and Sharpe ratio. In a finance context, this is dangerous because users may rely on the tool for calculations or education and receive materially incorrect guidance about how to evaluate investments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.