Security audit

Financial Model Forecast Reviewer

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a financial planning and forecasting assistant with some over-broad activation wording, but no evidence of hidden installation, persistence, credential handling, destructive behavior, or data exfiltration.

Before installing, treat this as a forecasting and planning helper rather than a source of regulated financial, tax, accounting, or investment advice. Use explicit prompts when you want it invoked, review any assumptions and outputs carefully, and avoid giving sensitive financial data unless you are comfortable sharing it with the agent runtime.

SkillSpector

By NVIDIA

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 (8)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrases are broad, malformed, and closely mirror generic user requests about finance, forecasts, and workflows. This increases the chance the skill will be invoked unintentionally for loosely related prompts, which can route users into an inappropriate workflow and cause incorrect financial guidance or unexpected handling of sensitive business-planning context.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger phrases are broad and generic enough to activate on common business or finance-related requests without clear boundaries, which can cause the skill to be invoked in unintended contexts. In an agent ecosystem, over-broad activation increases the chance of misrouting user tasks, overshadowing more appropriate skills, and processing sensitive financial planning requests without explicit user intent.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description is broad enough to match a wide range of ordinary business or finance questions, which can cause the agent to invoke this skill outside its intended niche. Over-broad activation is dangerous because it increases unintended tool routing, causing irrelevant guidance, reduced reliability, and potential bypass of more appropriate specialized skills or guardrails.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger keywords are generic terms like 'forecast', 'runway', and 'assumptions', which are common across many contexts and can easily cause accidental activation. In an agent system, ambiguous triggers create scope confusion and misrouting risk, especially when the skill claims broad business-and-operations applicability.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The skill description is broadly scoped across multiple business and finance tasks without clear boundaries, exclusions, or qualification criteria. This can cause over-triggering, leading the agent to invoke the skill for loosely related requests and potentially generate financial guidance in contexts where the user's needs, jurisdiction, risk tolerance, or data quality are unclear.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger keywords include generic terms like 'forecast', 'runway', and 'assumptions' without contextual constraints or negative examples. These terms are common in many domains, so the skill may activate on unrelated prompts and steer conversations into financial-model workflows inappropriately, increasing the chance of irrelevant, misleading, or overconfident assistance.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The default prompt is broad and generic, and the skill also allows implicit invocation, which increases the chance the agent will trigger this skill for loosely related business or finance requests without clear user intent. That can route sensitive planning or spreadsheet-related tasks into this skill unexpectedly, creating authorization, privacy, or workflow integrity risks even if the skill is not overtly malicious.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger sentences are broad, malformed, and close to ordinary user phrasing, which can cause the skill to activate in unintended contexts. That increases the chance the agent routes unrelated conversations into this skill, producing off-target financial guidance or overriding a more appropriate specialized workflow.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal