Security audit

Make Skill Template

Security checks across malware telemetry and agentic risk

Overview

This skill helps users create or update Codex skills and its file-writing behavior is disclosed, user-directed, and aligned with that purpose.

Install this only if you want an agent to help create or update local skills. Review proposed skill content and target paths before approving writes, because new skills can change future agent behavior and may include executable resources.

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

Medium

Confidence: 90% confidence
Finding: The frontmatter description uses broad trigger phrases such as "create a skill" and "make a new skill," which are common user requests and can cause this skill to be auto-invoked in situations where a more specific skill or direct response would be more appropriate. Overbroad activation increases the chance of unintended capability exposure and prompt-routing errors, even though the content itself is not overtly malicious.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The "When to Use This Skill" section contains ambiguous conditions like "add a specialized capability" and "help structuring a skill," which do not clearly bound when the skill should or should not activate. In a skill-discovery system, vague triggers can lead to accidental invocation and misrouting, reducing reliability and potentially surfacing instructions outside their intended context.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.