ClawHub
Back to skill

Security audit

accelerated-learning

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed learning-workflow skill that guides users through a structured 10-step study process without code execution, credential access, persistence, or hidden data handling.

Install this if you want a structured Chinese-language learning assistant. Expect it to steer broad learning or research requests into its 10-step workflow; no evidence was found of hidden code execution, credential access, persistence, or data exfiltration.

A.I.G

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

SkillSpector

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
97% confidence
Finding

The trigger phrases are very broad and map to common user intents such as 'learn', 'research', or 'understand a topic', which can cause the skill to activate for a wide range of ordinary conversations. In a skill-routing system, this creates overreach and misrouting risk: the skill may intercept requests better handled by other specialized or safety-constrained skills, leading to inappropriate responses or bypass of intended routing boundaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation logic says to start whenever the user mentions wanting to learn a topic, which is an ambiguous condition broad enough to match many everyday requests. Because this skill drives a structured multi-step process and can auto-chain dependent steps, accidental invocation could dominate conversations, create confusing user experiences, and interfere with safer or more context-appropriate skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.