ClawHub
Back to skill

Security audit

Whistleblower Ethics Hotline

Security checks for vulnerabilities and agentic risk

Overview

This is a static guidance skill for building whistleblower and ethics hotline workflows, with no code execution, persistence, credential handling, or hidden data access.

Review the generated policies with qualified legal or compliance counsel before use, especially because whistleblower obligations vary by jurisdiction and organization type. Treat any real hotline reports as sensitive data and evaluate third-party hotline vendors separately for privacy, retention, access control, and contractual safeguards.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The phrase "When activated" describes behavior after invocation but does not explain what specific user request or trigger should activate the skill. Without explicit trigger phrases, scope limits, or negative examples, the skill could be invoked in unintended contexts involving general ethics, compliance, or reporting questions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.