ClawHub
Back to skill

Security audit

Stock Research Desk

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed stock-research helper that uses web research and local document output for its stated purpose, with no artifact-backed evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Before installing, be aware that this skill may search external financial sources, run setup commands, use an OLLAMA_API_KEY from the environment, and write bilingual DOCX reports to the desktop. It should be used for research support only, not as trading execution or personalized portfolio management.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
94% confidence
Finding

The skill description is broadly phrased ('use when researching a stock, screening a sector, or maintaining a watchlist') without clear activation boundaries or guardrails, which can cause over-invocation in contexts involving finance. In a tool with Web access, Bash, and file-writing capability, ambiguous triggering increases the chance the agent performs unnecessary external fetching, local changes, or generates regulated-looking investment research when the user's intent is underspecified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The markdown states outputs are produced as bilingual DOCX files and the skill allows WebSearch/WebFetch, but it does not prominently warn users that the skill may access external websites and write files to the local system. This can surprise users, lead to unintended data egress through web queries, or cause unexpected file creation on the desktop, especially in environments where local artifacts or outbound access are sensitive.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.