ClawHub
Back to skill

Security audit

ALIWAY

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing-style skill with no code execution or data access, though its activation wording is broad enough that users should apply it deliberately.

Install this if you want a strong 阿里味 strategic writing style. Use explicit requests when invoking it, because its listed triggers are broad and the output may become more prescriptive or rhetorical than neutral writing.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
95% confidence
Finding

The skill advertises activation on a very broad set of generic phrases such as 'CTO视角', '使命愿景', '终局思维', and similar keywords, which can cause it to trigger in many normal writing or planning contexts where the user did not explicitly request this transformation. That creates a prompt-scope vulnerability: the assistant may unexpectedly switch into a strong prescriptive style, reducing user control and increasing the chance of irrelevant, misleading, or policy-conflicting output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description frames the skill as transforming 'any' document into a specific '阿里 P10' strategic narrative without indicating that the user should be asked whether they want that style applied. In practice, this can override the user's preferred tone, audience, or neutrality requirements, and the skill's forceful rhetoric may distort technical content or produce manipulative framing when a more balanced style is needed.

Content

No source excerpt is available for this finding.