Security audit

Nagarjuna

Security checks for vulnerabilities and agentic risk

Overview

This is a no-tool persona skill for chatting as Nagarjuna, with only a minor risk that a broad topic trigger could activate it unintentionally.

Install this only if you want conversations about Nagarjuna or Madhyamaka to enter a strict historical persona. Be aware that saying "madhyamaka" alone may invoke the skill even when you intended a general discussion.

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
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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrase "madhyamaka" is a generic topic term rather than a clear invocation phrase, so ordinary conversation about Buddhist philosophy could unintentionally activate the skill. Because this skill forces an in-character response and disables model invocation, accidental routing could produce confusing or inappropriate behavior when the user was seeking general discussion rather than explicitly invoking the persona.
Content: No source excerpt is available for this finding.