MyAider Skill Importer

• Outcome: Review
• Latest audit: Sep 11, 2026 · 1:33 AM UTC
• Version: 1.0.1

Overview

The skill is a coherent MyAider importer, but it can persist remote instructions as local skills and overwrite existing skills without full review or validation.

Use this only with a MyAider server and account you trust. It does not show malicious behavior, but it gives remote MyAider skill definitions a path to become persistent local agent instructions and to replace existing MyAider-derived skills. Manually review generated skills or diffs before creation or upgrade.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

Findings (1)

T01 · Skill Instruction Hijacking

Error

• Location: SKILL.md:74

Finding

Unvalidated Remote Instructions Can Be Installed as Persistent Agent Skills

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Self-Modification

High

• Category: Rogue Agent
• Confidence: 95% confidence

Finding

This skill directs the agent to upgrade skills by invoking another tool that will overwrite existing skill files with content sourced from a remote MCP server. Even though confirmation is required, this is a self-modification pathway that changes executable agent behavior and could propagate malicious or compromised remote skill definitions into the local environment.

Content

Scanner excerpt · SKILL.md (reported line 132)May include surrounding context.

md

Present the classification to the user (what will be upgraded, what is new, what is already current) and ask for confirmation before proceeding.

### Upgrade Step 4 — Upgrade outdated skills
For each skill marked for **upgrade**, invoke `skill-creator:skill-creator` with the full updated specification (same template as the main Step 3, including refreshed `updated_at` and tool schemas). skill-creator will overwrite the existing skill file.

### Upgrade Step 5 — Install new skills
For each skill marked for **new install**, invoke `skill-creator:skill-creator` exactly as in the main Step 3 (import workflow).

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The top-level skill description does not clearly warn that running the skill will create new local skill files and may overwrite existing ones during upgrades. This omission can mislead users or downstream agents about the side effects of invoking the skill, increasing the risk of accidental modification of the local skill set.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The example invocation phrases are broad enough that the skill could be triggered in contexts where the user has not clearly scoped whether they want import, creation, or upgrade behavior. Because this skill performs file-writing actions and can overwrite existing skills, ambiguous triggering increases the chance of unintended local modifications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.