ClawHub
Back to skill

Security audit

IR Playbook Generator

Security checks for vulnerabilities and agentic risk

Overview

This API skill is coherent for generating incident-response playbooks, but it sends potentially sensitive organizational security information to an external service without enough documented scoping or data-protection controls.

Review this carefully before installing or using it. Do not submit real incident evidence, credentials, tokens, private keys, regulated personal data, emergency contact lists, or detailed internal system inventories unless you have vetted the external provider's security, retention, deletion, data residency, and access-control practices.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
openapi.json:91
Finding

Unrestricted Transmission of Potentially Sensitive Assessment Data Without Documented Security Controls

Content
View full analysis

Vulnerability Details

File Location: openapi.json:91-125; related external service references at SKILL.md:238-241 and request example at SKILL.md:21-37
Vulnerability Type: Unrestricted sensitive-data input and missing API security configuration
Risk Level: Medium

Vulnerable Code

json
"PlaybookRequest": {
  "properties": {
    "assessmentData": {
      "type": "object",
      "title": "Assessmentdata"
    },
    "sessionId": {
      "type": "string",
      "title": "Sessionid"
    },
    "userId": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Userid"
    },
    "timestamp": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Timestamp"
    }
  },
  "type": "object",
  "required": [
    "assessmentData",
    "sessionId"
  ],
  "title": "PlaybookRequest"
}

The documented destination is an external service:

markdown
- **Kong Route:** https://api.mkkpro.com/security/ir-playbook-generator
- **API Docs:** https://api.mkkpro.com:8118/docs

The documented request demonstrates that the unrestricted object may contain sensitive organizational security information:

json
{
  "assessmentData": {
    "organization_name": "TechCorp Inc.",
    "industry": "Financial Services",
    "employee_count": 2500,
    "critical_systems": ["Payment Processing", "Customer Database", "Internal Email"],
    "compliance_frameworks": ["PCI-DSS", "SOC 2", "GDPR"],
    "current_ir_maturity": "Intermediate",
    "primary_threats": ["Ransomware", "Data Exfiltration", "Insider Threats"]
  },
  "sessionId": "sess_abc123def456",
  "userId": 42,
  "timestamp": "2024-01-15T10:30:00Z"
}

Technical Analysis

assessmentData is defined only ...[truncated 2815 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace the generic assessmentData object with an explicit schema listing every accepted field, type, length, and array limit.
  2. Set additionalProperties: false on the request object and appropriate nested objects to reject undeclared content.
  3. Explicitly prohibit credentials, access tokens, private keys, raw forensic evidence, unnecessary personal data, and other secrets.
  4. Add payload-size, nesting-depth, string-length, and array-length limits.
  5. Define an OpenAPI securitySchemes entry for an appropriate authentication mechanism and apply a security requirement to /api/ir/playbook.
  6. Enforce server-side authorization, tenant isolation, rate limiting, and audit logging. Avoid placing sensitive request bodies in logs.
  7. Apply server-side validation and redaction rather than relying exclusively on client behavior.
  8. Clearly disclose the external processing destination, data usage, retention period, deletion procedure, subprocessors, and confidentiality guarantees before submission.
  9. Require affirmative user confirmation before transmitting organizational security information to the external service.
  10. Document and enforce TLS certificate validation and modern transport-security settings.
  11. Add automated contract tests verifying rejection of undeclared fields, oversized payloads, secrets, and unauthenticated requests.

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
93% confidence
Finding

The skill embeds realistic examples of sensitive organizational and personal data, including named contacts, email addresses, phone numbers, compliance posture, critical systems, and threat priorities, without any warning that such data should be fictionalized or handled carefully. In a security-focused skill, users may copy real incident-response contact lists or internal environment details into requests, increasing the risk of privacy exposure, oversharing to a third-party API, and leakage of operationally useful intelligence.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
76% confidence
Finding

The skill directs users to an external API endpoint, which implies transmission of detailed assessment data and potentially sensitive incident-response information to a third-party service. Given the nature of the payloads described in the skill, this external transmission increases data exposure risk if the endpoint's trustworthiness, retention practices, tenant isolation, and transport/security guarantees are not clearly documented and vetted.

Content

Scanner excerpt · SKILL.md (reported line 240)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/security/ir-playbook-generator
- **API Docs:** https://api.mkkpro.com:8118/docs