ClawHub
Back to skill

Security audit

risk-assessment

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent risk-assessment prompt package; the main caution is that users may provide sensitive security or regulated data to an LLM provider when using it.

Install only if you are comfortable using an LLM-assisted process for security risk assessments. Do not provide live secrets, credentials, unnecessary personal data, or regulated records unless your organization has approved that model/provider workflow and data handling policy.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · examples/example_output.json (reported line 7)May include surrounding context.

json
"risk_id": "RSK-001",
      "asset_or_system": "Remote Access Portal / EHR Database",
      "asset_classification": "regulated_data",
      "threat_event": "Compromise of remote access credentials via phishing, credential stuffing, or brute force.",
      "vulnerability": "Absence of Multi-Factor Authentication (MFA) for remote access to systems containing sensitive regulated data.",
      "framework_control_mapping": {
        "framework": "NIST CSF 2.0",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example sends the full user-supplied risk assessment context directly to the Anthropic API as part of the prompt, with no warning, consent flow, redaction, or data classification checks. In this skill’s context, the input is likely to contain sensitive security, operational, compliance, or regulated data, so transmitting it to a third-party model provider can create confidentiality, privacy, and compliance exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.