ClawHub
Back to skill

Security audit

Compliance & Audit Readiness Engine

Security checks for vulnerabilities and agentic risk

Overview

This is an informational compliance checklist skill whose sensitive-topic prompts are expected for audit readiness, but users should avoid pasting secrets or raw regulated records into it.

Install only if you want checklist-style compliance and audit readiness help. Treat it as planning support, not legal or audit advice, and keep real customer data, secrets, raw incident details, pentest findings, access lists, and contractual documents in approved secure repositories with least-privilege access.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly asks users to provide detailed organizational, regulatory, and data-handling information, including sensitive categories like health data, payment data, biometric data, and government/classified data, but gives no warning about confidentiality, minimization, or safe handling. In a compliance context, users may paste real internal details, creating avoidable exposure of sensitive business and regulated-information metadata to the agent or downstream systems.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The evidence-collection section encourages assembling a centralized repository of highly sensitive audit artifacts such as access reviews, vulnerability scan reports, pentest reports, incident logs, vendor assessments, and DPAs/BAAs, but provides no confidentiality, access-control, or retention guidance. If users follow this literally in an insecure or overshared workspace, it could expose a detailed map of security weaknesses, identities, contracts, and incident history that materially increases attacker leverage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.