ClawHub
Back to skill

Security audit

threat-intelligence

Security checks for vulnerabilities and agentic risk

Overview

This threat-intelligence skill is very minimal and not malicious, but it is too broadly scoped and unclear about what code or external service will handle potentially sensitive security inputs.

Review before installing. Use this only if you understand which threat-intelligence script and provider will run, where INTEL_API_KEY is stored, and whether submitted indicators, internal domains, incident details, or artifacts may be sent to a third party. The package should ideally include the referenced script and add clear external-data and credential-handling disclosures.

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, when-to-use guidance, and generic phrasing are broad enough that an orchestrator or user may invoke this skill for loosely related 'threat' or 'security' tasks without clear boundaries. That increases the chance of unintended execution and unnecessary transmission of user-supplied data to backend tooling or services, especially in automated security workflows where sensitive indicators or incident details may be passed through.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation tells operators to configure an API key and run a threat-intelligence script, but it does not warn that submitted inputs may be sent to an external service. In a security context, those inputs can include sensitive indicators, investigation details, internal domains, or incident artifacts, so omission of a disclosure meaningfully raises data leakage and credential-handling risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.