Security audit

Ten Defeats

Security checks across malware telemetry and agentic risk

Overview

This skill is a broad software-work guardrail that may activate often, but its artifacts are transparent and do not add hidden execution, data access, persistence, or credential handling.

Install this if you want Codex to apply a general quality-control workflow automatically on non-trivial software tasks. Be aware it may shape planning and completion behavior often because implicit invocation is enabled and the trigger is broad.

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 (2)

Vague Triggers

High

Confidence: 91% confidence
Finding: The trigger description is unusually broad and can cause this skill to activate for a wide range of normal software tasks, effectively increasing its influence over many interactions. While the content is framed as process guidance rather than obviously malicious behavior, over-broad activation creates an attack surface for instruction shadowing, unnecessary tool use, or workflow takeover if the skill is later modified or combined with weaker controls.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill enables implicit invocation with only broad descriptive guidance and no concrete, enforceable activation constraints. That can cause the agent to auto-apply this skill in situations beyond the intended scope, influencing planning and completion judgments without explicit user intent or narrowly defined triggers.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.