ClawHub
Back to skill

Security audit

MITRE ATT&CK Technique Mapper

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says, but it can send sensitive security reports and incident details to an external ToolWeb API without enough consent, redaction, or data-handling guidance.

Before installing, treat this as an external data-processing integration. Only submit reports or logs you are authorized to share with ToolWeb, redact secrets and unnecessary internal details, use a revocable scoped API key, and check the provider's privacy, retention, and deletion terms.

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
Findings (1)

other

Warning
Location
SKILL.md:27
Finding

Potential Disclosure of Sensitive Security Reports to an External Service

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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)

YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.

": "Monitor for net user, whoami /all, Get-LocalUser execution", "mitigations": ["M1028 - Operating System Configuration"] }, { "technique_id": "T1003.001", "technique_name": "OS Credential Dumping: LSASS Memory", "tactic": "Credential Access", "confidence": 0.97, "detection": "Monitor for lsass.exe memory access (Sysmon Event ID 10); alert on procdump, mimikatz, Task Manager targeting lsass", "mitigations": ["M1043 - Credential Access Protection", "M1028 - Operating System Configuration", "M1026 - Privileged Account Management"] } ], "threat_actor_associations": ["APT29", "FIN7", "Lazarus Group"], "kill_chain_coverage": ["Initial Access", "Execution", "Discovery", "Credential Access"] }

text

---

## API Reference

**Base URL:** `https://portal.toolweb.in/apis/security/mitre-attack-mapper`

| Endpoint | Method | Content-Type | Description |
|----------|--------|--------------|-------------|
| `/map-technique` | POST | `multipa

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs users to submit free-text incident details and upload reports to a third-party API endpoint, but it does not warn that potentially sensitive security data will leave the local environment. This creates a real data exposure and consent risk because users may unknowingly transmit incident reports, logs, or threat intelligence containing confidential internal information to an external service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.