ClawHub
Back to skill

Security audit

AI Agent Stack Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent external API skill for AI stack recommendations, with no local execution or persistence, but users should avoid sending sensitive project or compliance details.

Use this as a third-party recommendation API. Do not include secrets, patient data, customer records, proprietary architecture details, or unnecessary personal identifiers in additionalNotes; prefer pseudonymous session and user identifiers where possible.

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
93% confidence
Finding

The sample request includes persistent identifiers (sessionId, userId, timestamp) alongside potentially sensitive business and compliance details such as healthcare use and HIPAA requirements, but the documentation provides no privacy, minimization, retention, or redaction guidance. This can normalize sending linkable metadata and regulated-context information to the service, increasing the risk of unnecessary collection, logging, and downstream disclosure.

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 252)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/creative/ai-agent-stack-builder
- **API Docs:** https://api.mkkpro.com:8162/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This is a manifest file, so vague-trigger checks apply. The description "Generate AI agent technology stack recommendation" is broad and does not define constraints, exclusions, or a narrower activation context, which could allow overly loose matching in systems that derive invocation behavior from OpenAPI metadata.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

For markdown and code files, missing-warning checks apply differently, but this file is a manifest file so SQP-2 does not apply. The OpenAPI spec declares fields like sessionId, userId, and timestamp, yet provides no description warning that these identifiers may be collected or transmitted when calling the endpoint.

Content

No source excerpt is available for this finding.