ClawHub
Back to skill

Security audit

tantan-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a simple market-intelligence prompt skill with broad routing language but no code, persistence, credentials, or hidden high-impact behavior.

Install this if you want a Chinese market-analysis briefing template. Be aware that its activation wording is broad, so it may be invoked for many market or competitor questions; users who need multilingual behavior or narrower routing may want the publisher to clarify those points.

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

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation rule is explicitly broad: it says the skill must trigger whenever the user wants to understand external market conditions, using a wide set of common keywords. This can cause the skill to intercept loosely related requests without clear scoping, increasing the chance of unintended routing, policy bypass of more appropriate skills, or over-collection/over-generation of market intelligence where the user did not clearly ask for it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill metadata and content are written entirely in Chinese and instruct activation in that mode, but there is no statement that language should follow user preference or that this is a region-specific skill. Under the policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.