dca-decision-calculator

• Outcome: Review
• Latest audit: Aug 5, 2026 · 3:38 PM UTC
• Version: 1.0.0

Overview

This is a disclosed finance calculator, but its broad activation terms and action-oriented investment and exchange guidance make it a Review item rather than a routine install.

Install only if you want an assistant to provide structured investment and exchange decision support. Treat outputs as calculations and prompts for your own review, not as financial advice, and be careful if generic finance terms in conversation could trigger it unexpectedly.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (22)

Intent-Code Divergence

Medium

• Confidence: 84% confidence
• Finding: The skill’s rules conflict on whether it may proceed with incomplete inputs: it says to never give operational guidance before collecting required data, but later allows defaulting missing cost/budget fields to 0 and still computing outputs. In a finance skill, this inconsistency can cause the agent to produce seemingly authoritative buy/add-position guidance from incomplete user data, increasing the risk of unsuitable financial actions.

Intent-Code Divergence

Medium

• Confidence: 78% confidence
• Finding: The skill claims it does not predict exchange rates, yet its exchange-mode logic tells users to wait, split, or accelerate conversion based on comparisons to historical average cost. That crosses from neutral calculation into timing guidance, which may be interpreted as implicit forecasting or market advice despite the stated limitation.

Description-Behavior Mismatch

Medium

• Confidence: 81% confidence
• Finding: The manifest presents a narrow calculator for left-side DCA decisions, but the body expands into valuation analysis, intrinsic value estimation, trend-based judgment, and portfolio health recommendations. This scope creep makes the skill more powerful than advertised and can cause it to activate or be trusted in contexts where users expect only arithmetic, not broader investment analysis.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger list is broad enough to match many ordinary finance conversations, which can cause the skill to activate outside the user's clear intent. In an investment-related skill, unintended invocation is risky because it may inject financial guidance or recommendations into unrelated discussions, increasing the chance of inappropriate or unsolicited advice.

Vague Triggers

High

• Confidence: 93% confidence
• Finding: The trigger inventory is very broad and consists of common finance words that may appear in ordinary conversation. This raises the chance of unintended activation, causing the skill to inject investment or exchange guidance into unrelated chats, which is especially risky in a finance context because users may act on unsolicited recommendations.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The manifest trigger entries are short, ambiguous, and lack constraints such as required co-occurring terms, numeric inputs, or explicit user intent. In a financial advisory-adjacent skill, accidental activation can expose users to unsolicited strategy outputs or data collection prompts in conversations that merely mention investing.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger table’s activation logic is underconstrained because broad keyword matches alone can route users into decision, exchange, holding-diagnosis, or strategy modes. Ambiguous routing in a finance skill can produce the wrong type of analysis or escalate from harmless discussion into actionable investment guidance without clear user intent.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 90% confidence
• Finding: The trigger '定投' is a very short, common term and can match many ordinary investment discussions. While not malicious by itself, in this skill it contributes to accidental activation of financial guidance flows, which makes even low-specificity triggers more dangerous than in non-sensitive domains.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 90% confidence
• Finding: The trigger '基金' is highly generic and likely to appear in many unrelated or exploratory conversations about finance. In this skill context, that broadness can lead to unsolicited activation and collection of investment-related inputs or strategy outputs.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 89% confidence
• Finding: The trigger '指数' is extremely broad and may match market news, education, or casual conversation. Because this skill produces strategy-oriented outputs, broad activation on such a common term can steer general discussion into investment decision support unexpectedly.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 90% confidence
• Finding: The trigger '加仓' is short and common in investing conversations, including hypothetical or retrospective discussions. In a finance skill, standalone matching can cause the assistant to move into action-oriented guidance without confirming whether the user wants a calculation.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 90% confidence
• Finding: The trigger '换汇' is generic and may appear in many informational discussions unrelated to this calculator. Given that the skill offers timing-oriented conversion suggestions, accidental activation on a short trigger can expose users to unwanted financial guidance.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 88% confidence
• Finding: The trigger '汇率' is a very common financial term and can appear in news, translation, travel, or education contexts. Its low specificity increases unintended activation risk, which is more serious here because the skill can offer actionable exchange-related suggestions.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 89% confidence
• Finding: The trigger '投资' is overly general and likely to appear in countless broad conversations. In a skill that goes beyond arithmetic into strategy and valuation commentary, such broad triggering can surface financial guidance unexpectedly.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 88% confidence
• Finding: The trigger '买入' is generic and appears in many discussions ranging from news commentary to hypothetical questions. In this skill context, that can lead to unsolicited decision support or add-position calculations without clear request boundaries.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 89% confidence
• Finding: The trigger '持仓' is common in portfolio discussions and can match benign status-sharing rather than a request for analysis. Since the skill can escalate into health ratings and strategy advice, using the standalone term creates unnecessary activation risk.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 88% confidence
• Finding: The trigger '成本' is extremely broad and appears in many non-financial contexts as well. Broad matching on such a generic word can activate the skill in unrelated discussions and produce irrelevant or intrusive financial prompts.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 85% confidence
• Finding: The trigger '跌了' is colloquial and broadly used in casual conversation about many assets or even non-financial topics. It is too ambiguous to safely activate a strategy calculator that may respond with action-oriented outputs.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 85% confidence
• Finding: The trigger '涨了' is similarly ambiguous and likely to appear in general market chatter. In this skill, using it as a standalone trigger can route users into investment analysis even when they are merely making an observation.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 87% confidence
• Finding: The trigger '跌幅' is short and common in analytical or news contexts. Because the skill can produce portfolio and buy/add guidance, activation on this single term alone is overly permissive for a sensitive finance domain.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 72% confidence
• Finding: The trigger '缩水' is colloquial and somewhat broader than the intended DCA use case, but it is less clearly finance-specific than others. It still presents some accidental activation risk because users may use it metaphorically or in unrelated contexts.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 86% confidence
• Finding: The trigger '估值' is a common analysis term that can arise in education, news, or general discussion. Since this skill expands into valuation judgments, broad activation on the term can prompt unsolicited analytical outputs beyond the advertised calculator role.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.