my-skill-name

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:40 PM UTC
• Version: 2.0.0

Overview

This is a local helper for creating, validating, and packaging AgentSkills, and its file-writing behavior matches that purpose.

Install this only if you want Codex to help create or maintain AgentSkills. Expect it to create local skill folders, edit SKILL.md files, run bundled helper scripts, and build .skill archives when used; review target paths and any newly created scripts before execution.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 80% confidence
• Finding: The skill instructs the agent to run local scripts, edit files, and package artifacts, which implies shell, file read/write, and possibly network-capable execution, yet no permissions are explicitly declared. That creates an authorization and transparency gap: a caller may invoke a skill with broader operational capability than its metadata suggests, increasing the chance of unsafe execution or misuse.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The description presents the skill as a general creator/editor/auditor for skills, but the body also directs packaging and validation operations with security-relevant filesystem behavior. This mismatch can mislead routing and user expectations, causing the skill to be triggered in contexts where archive creation, validation, or other side effects are unexpected.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The skill description includes broad trigger phrases such as creating, improving, reviewing, cleaning up, or auditing a skill. In an agent-routing system, overly broad metadata can cause the skill to activate for loosely related requests, pulling in instructions that modify files or restructure directories when the user did not intend that workflow. The risk is increased because this is a meta-skill that authorizes creation and refactoring of other skills, so misrouting can lead to unintended edits across a skill repository.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger description includes broad phrases like creating, improving, reviewing, auditing, cleaning up, and restructuring a skill, which can match many benign editing requests. Overbroad activation increases the chance that a high-capability skill is loaded unnecessarily, exposing powerful instructions such as script execution and packaging in situations that did not require them.

Self-Modification

High

• Category: Rogue Agent

Content

1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Initialize the skill (run init_skill.py)
4. Edit the skill (implement resources and write SKILL.md)
5. Package the skill (run package_skill.py)
6. Iterate based on real usage

• Confidence: 90% confidence
• Finding: write SKILL

Self-Modification

High

• Category: Rogue Agent

Content

If you used `--examples`, delete any placeholder files that are not needed for the skill. Only create resource directories that are actually required.

#### Update SKILL.md

**Writing Guidelines:** Always use imperative/infinitive form.

• Confidence: 92% confidence
• Finding: Update SKILL

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.