ClawHub
Back to skill

Security audit

紫苏叶·瓶颈猎手 | ShisoLeaf Alpha

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only investment research framework with clear disclaimers and no code, persistence, credentials, or hidden execution behavior.

Before installing, understand that this skill can shape investment analysis around a specific high-risk bottleneck-investing framework. Do not provide credentials, brokerage information, or private holdings, and verify any market claims against current official filings and qualified financial advice.

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
89% confidence
Finding

The manifest description includes very broad activation cues such as 'bottleneck hunting', 'stock-analysis', and 'supply-chain' that can match generic analysis requests far beyond the narrow intended methodology. This increases the chance the skill is invoked in contexts where the user did not explicitly ask for this investment framework, causing unintended steering of outputs and possible interference with other skills or system behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest description is written primarily in Chinese with embedded English terms, but nowhere indicates that users may choose their preferred response language. Under the language/locale policy, a skill should not implicitly force a language style unless it offers opt-in or clearly documents a justified locale constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.