Back to skill

Security audit

Self Learning Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a coaching-style learning and productivity skill with broad wording but no hidden code, tool use, persistence, or sensitive access.

Install this if you want the assistant to frame learning and work questions around diagnosis, action plans, and feedback loops. Expect it to be somewhat opinionated and broadly applicable to productivity conversations, but it does not appear to add code, background behavior, or access to private data.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description states the skill 'turns learning, work, and execution into a continuous improvement system' without defining scope, boundaries, or explicit activation constraints. Broad, open-ended descriptions can cause an agent to over-apply the skill in unrelated contexts, increasing the risk of unintended autonomy, prompt injection exposure, or unsafe task expansion.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The listing describes the skill as helping users improve how they learn, think, and execute, and says it is useful for 'anyone who wants to learn faster and execute better.' In a manifest-style listing, this scope is very broad and lacks concrete trigger boundaries or exclusion conditions, which could cause the skill to match common self-improvement or productivity requests too generally.

Content

No source excerpt is available for this finding.