ClawHub
Back to skill

Security audit

Get company fact and information by ticker or CIK

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward public-company lookup helper that uses a disclosed third-party API and does not include executable code, persistence, or hidden behavior.

Before installing, understand that company names, tickers, or CIKs you ask about will be sent to apipick using your API key and may consume credits. Avoid using it for confidential watchlists or non-public research targets unless that sharing is acceptable under your policies.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README explains that queries use an API key and a third-party endpoint, but it does not clearly warn that user-supplied company queries will be transmitted to apipick. In an agent context, users may assume prompts are handled locally or by the primary platform, so missing disclosure can cause unintended sharing of potentially sensitive watchlists, research interests, or internal investigation targets with an external service.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file describes activation as 'just ask your AI agent naturally' and provides example prompts like 'Look up company info for Apple' and 'How many employees does Microsoft have?' These phrases overlap with ordinary conversation and do not specify when the skill should or should not activate, which can cause unintended invocation in systems that rely on natural-language matching.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.