ClawHub
Back to skill

Security audit

analyst-wkh

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown skill for structured US equity research, with no executable code, persistence, account access, or hidden behavior found.

Before relying on this skill, treat its output as research support rather than financial advice, verify market data from current sources, and be cautious with any optional trade-plan suggestions because the skill does not execute trades or validate suitability for your personal finances.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file specifies language: en-US, which imposes a specific language/locale. Under the policy, locale constraints should either be user-selectable or clearly justified as region-specific; this file focuses on US stocks but does not explicitly justify restricting output language to English or offer opt-in/out.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.