Security audit

Modern Chanakya

Security checks across malware telemetry and agentic risk

Overview

This is a broad Chanakya-style advice skill with some routing and over-reliance cautions, but it does not show hidden access, data theft, destructive behavior, or unsafe installation behavior.

Install this only if you want broad Chanakya-style strategic framing. Treat outputs about health, finances, legal issues, relationships, or emergencies as general perspective rather than professional advice, and avoid putting private personal details into any reusable knowledge layer.

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 (7)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger principle is broad enough to match many ordinary conversations about work, health, money, relationships, and risk, which increases the chance of unintended skill activation. In an agent system, overly permissive triggering can route user input to the wrong capability, causing inappropriate advice, scope overreach, and unreliable behavior across sensitive domains.

Vague Triggers

Medium

Confidence: 97% confidence
Finding: Many phrases in the trigger clusters are extremely generic, such as 'burnout,' 'uncertainty,' 'difficult conversation,' or 'best grocery option,' making accidental invocation likely. Because this skill spans career, health, wealth, relationships, negotiation, and practical life topics, broad trigger matching creates a meaningful risk of misclassification and delivery of advice outside the user’s intended context.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: Short-form examples like 'Give me the strategic answer' or 'What is the smartest move?' are common prompts that could appear in normal conversation without any intent to invoke this specific skill. This makes the skill easier to trigger unintentionally, which is more dangerous here because the skill presents itself as authoritative guidance across multiple sensitive life and work areas.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The quick prompts are extremely short and generic (for example, 'analyze this', 'repair this', and 'risk view'), which increases the chance that ordinary user text could unintentionally trigger this skill or cause ambiguous routing in a larger agent system. In a skill that provides strategic, advisory guidance across many domains, broad triggers expand the activation surface and can lead to misclassification, unintended invocation, or policy-bypassing context switches if the orchestrator relies on phrase matching.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The invocation criteria are framed in very generic terms like 'strategic advice', 'tradeoff handling', and 'real-world judgment under pressure', which can match a large share of ordinary user requests. In an agent-routing context, this can cause the skill to be invoked for sensitive or unrelated situations where it may provide broad life, financial, health, or relationship guidance without appropriate domain constraints.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The skill purpose spans many life domains including health, wealth, relationships, negotiation, reputation, and practical decision-making, making its scope ambiguous and overly expansive. This increases the chance that the agent treats the skill as a catch-all advisor, which is risky because users may receive quasi-expert guidance in high-stakes domains without proper boundaries or specialized safety handling.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The guide invites use in sensitive domains affecting wellbeing, finances, family stability, and conflict resolution, but provides no warnings, escalation rules, or limitations for potentially harmful advice. In context, this is more dangerous because the skill is designed to influence judgment and action across personal life domains, so omission of safety boundaries can lead users to over-rely on generalized strategic advice during vulnerable or high-stakes situations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.