Back to skill

Security audit

Learning Topic Whiteboard Map

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only learning map skill with no code, network access, credentials, persistence, or sensitive data handling.

Before installing, consider that the skill is English-focused and may activate for broad study or concept-map requests. It appears safe for organizing learning notes, but users should still verify factual claims with reliable sources, especially for regulated or high-stakes topics.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file includes natural-language requirements that the skill declare language=en and that public-facing documentation be English only. The policy allows locale constraints only when users are offered a choice or when the restriction is clearly documented and justified as region-specific, neither of which is present here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This manifest defines trigger keywords such as "concept map", "topic breakdown", and "learn a hard topic" that are broad natural-language phrases rather than narrowly scoped invocation terms. The file does not provide exclusion conditions or negative examples, so these phrases could match ordinary educational requests and cause unintended activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest sets the skill language to "en", which indicates an English-only constraint. There is no nearby documentation in this file that offers language choice or explains a justified region- or compliance-specific reason for the restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.