ClawHub
Back to skill

Security audit

Equity Analyst Test

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Korean-stock analysis skill with a local scoring script, but users should treat its BUY/HOLD/AVOID labels as informational rather than financial advice.

Use this skill only for Korean KRX equity research. Verify current market data independently, do not rely on its scores as personalized financial advice, and avoid pointing --output at an existing file unless overwriting it is acceptable.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill produces explicit investment attractiveness scores and BUY/HOLD/AVOID-style recommendations, but it does not include a clear warning that the output can materially influence financial decisions and may be incomplete, outdated, or unsuitable for the user. In this context, the structured scoring framework and authoritative tone increase the likelihood of over-reliance, which makes the omission safety-relevant rather than merely cosmetic.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file embeds Korean-specific sample data and mixes Korean-language sentiment and chart keywords in its scoring logic, but does not state that the skill is region- or language-specific or provide any user opt-in for locale assumptions. This can create a locale policy issue because behavior is partially specialized to a specific language context without explicit choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The manifest description defines the skill as '전문 투자 분석가 AI' and specifies Korean trigger phrases, indicating a fixed Korean-language interaction model. Because there is no explicit opt-in or alternative language choice documented, this can violate the language/locale policy criterion for forcing a specific language without user choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code opens the user-specified output path in write mode and writes the generated report, which can overwrite an existing file. Although the operation is visible in code, there is no confirmation prompt or user-facing warning about the overwrite behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.