Back to skill

Security audit

紫苏叶选股法 Perilla Leaf Screener

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed stock-research workflow skill with no executable code, persistence, credential access, or hidden local authority.

Install only if you want a Chinese-language workflow that helps generate high-risk stock research leads from public web sources. Treat outputs as research prompts, verify company filings and source links yourself, and do not treat the ranked candidates as investment advice.

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
95% confidence
Finding

The trigger list contains broad terms like 'Serenity', '挖标的', and '供应链瓶颈' that can match ordinary investment-research requests well beyond the narrowly described methodology. This can cause the skill to activate unexpectedly and steer general financial conversations into a prescriptive stock-screening workflow, increasing the chance of inappropriate or overconfident financial guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language description and instructions are entirely in Chinese and present the skill as operating in that language, but there is no statement that users may choose another language or that Chinese is required for a region-specific compliance reason. Under the policy, forcing a specific language without user opt-in is a locale-policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.