Security audit

master-curriculum

Security checks across malware telemetry and agentic risk

Overview

This skill is a static Buddhist study-path guide with no code execution, data access, persistence, or hidden system-level behavior.

Install this if you want a structured Buddhist study-path helper. Treat its religious curriculum recommendations as educational guidance, verify source references independently, and rely on qualified teachers for formal practice guidance.

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 (6)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger list is broad and consists mostly of common Chan/Zen terms without clear activation boundaries, exclusions, or intent checks. In a routing system, this can cause the curriculum skill to activate for generic doctrinal discussion or comparative requests, leading to incorrect tool selection, confused responses, and reduced reliability of downstream behavior.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger list is broad and consists mostly of high-level tradition and topic terms without clear activation boundaries, so the skill could be invoked for loosely related queries rather than explicit curriculum-planning requests. In this skill ecosystem, that can cause routing confusion and over-selection of this skill, especially for comparison or debate requests that should go elsewhere.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger list is broad and consists of common Buddhist terms without activation boundaries, disambiguation rules, or negative examples. In a multi-skill agent, this can cause over-triggering on general religious discussion and route users into a curriculum skill when they asked for comparison, debate, or unrelated content, creating prompt-routing confusion and reducing reliability.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger list includes very broad, high-frequency concepts such as “空”, “中道”, and “般若”, which can appear in many Buddhist or general philosophical queries outside the intended Sanlun/Madhyamaka scope. This can cause the agent to route users into this skill incorrectly, leading to irrelevant or biased guidance and reducing reliability of downstream responses.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger list is broad and mostly unconstrained, so the skill may activate for general Buddhist, meditation, or canon-related queries that do not actually ask for a sequenced curriculum. This can cause misrouting to this skill instead of a more appropriate one, producing incorrect or overly prescriptive guidance and reducing routing reliability.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger list is broad and consists of common doctrinal terms without explicit routing constraints, which can cause this skill to activate for queries that are merely about Tiantai concepts rather than curriculum planning. In an agent setting, overbroad activation can misroute user requests away from more appropriate skills, reducing reliability and potentially shaping answers in unintended ways.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.