ClawHub
Back to skill

Security audit

Security Stack Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a hosted API skill for security-stack recommendations, with disclosed external API use and no local execution or persistence, though users should be mindful that organization and tracking fields are sent to the provider.

Before installing, confirm you are comfortable sending organizational security context, compliance needs, session identifiers, timestamps, and optional user IDs to the provider's hosted API. Do not include secrets, internal architecture details beyond what is needed, or regulated personal data unless you have appropriate vendor/privacy approval.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill schema explicitly includes sessionId, userId, and timestamp fields that enable tracking or correlation of user activity, but the documentation does not disclose why this data is collected, how it is used, whether it is retained, or whether it is shared with third parties. In a security-focused product, omission of telemetry/privacy disclosure is risky because users may provide identifying metadata under the assumption that only recommendation logic is being performed.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.

md
## References

- Kong Route: https://api.mkkpro.com/security/security-stack-builder
- API Docs: https://api.mkkpro.com:8122/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This is a manifest/config file, so vague-trigger review applies. The description 'Generate personalized security stack recommendations' does not specify input constraints, scope boundaries, or exclusion conditions, which makes the activation/use condition for this operation broad and underspecified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.