Back to skill

Security audit

Adaptive Suite.Bak

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it asks for broad always-on assistance plus NAS metadata scanning without clear limits or user controls.

Review this skill carefully before installing. Use it only with explicit task boundaries, do not grant broad NAS paths by default, and avoid providing API keys unless you understand which external resources will be contacted and how any collected metadata will be stored.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is extremely broad, advertising capabilities across coding, business analysis, web development, data analysis, and NAS scraping without clear trigger boundaries. In an agent system, this increases the chance of over-activation or inappropriate invocation for unrelated tasks, which can expand access to tools and data beyond what a narrower skill would need.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction to 'continuously search for free online tools, APIs, and resources' creates an open-ended mandate for external discovery and network use. This can cause the agent to fetch unvetted third-party resources, increase exposure to prompt injection or malicious content, and blur the boundary between user-requested assistance and autonomous browsing behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill includes NAS directory scanning and metadata collection but does not clearly warn users that sensitive file names, paths, and metadata may be enumerated. Even in read-only mode, this can expose confidential information about system structure, project names, personal data, or regulated content, especially on shared or enterprise storage.

Content

No source excerpt is available for this finding.