ClawHub
Back to skill

Security audit

Data Breach Response

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-aligned, but it sends sensitive breach-response context to a third-party API without enough privacy, retention, or handling disclosure.

Review the provider and API terms before installing or using this skill. Avoid sending real breach details, exact tool inventories, regulated-data specifics, company names, user IDs, or session identifiers unless your organization has approved that third-party data sharing.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly solicits and transmits highly sensitive organizational context, including regulated data categories, deployed security tools, compliance obligations, company identity, session identifiers, timestamps, and optional user identifiers, but provides no privacy notice, data minimization guidance, retention policy, or handling constraints. In a security incident-response context, this metadata is especially sensitive because it can reveal an organization's defensive posture and regulated data exposure, increasing harm if the external service is compromised, misused, or logged insecurely.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The skill references an external API endpoint, meaning organizational breach-assessment data will be transmitted outside the local trust boundary to a third-party service. While external APIs are expected for this type of skill, the danger is elevated here because the transmitted content includes sensitive incident-response and compliance information, and the skill does not document trust, jurisdiction, authentication, encryption expectations, or data-handling guarantees.

Content

Scanner excerpt · SKILL.md (reported line 223)May include surrounding context.

md
## References

- Kong Route: https://api.mkkpro.com/security/data-breach-response
- API Docs: https://api.mkkpro.com:8106/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The schema requests potentially sensitive organizational and session-identifying data such as company name, industry, compliance context, sessionId, and timestamp, yet the API description provides no notice about transmission, storage, retention, or privacy handling. In a breach-response context, these fields can reveal incident-sensitive business information, increasing the risk of unintended disclosure or unsafe use by downstream consumers.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This is a manifest-type file, so vague-trigger rules apply. The description "Generate personalized data breach response plan" is broad and does not define what inputs, contexts, or limits distinguish appropriate use, which can contribute to unintended or overly broad activation in systems that rely on manifest text for routing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.