ClawHub
Back to skill

Security audit

Quantum Tech

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent hosted API integration for quantum career roadmap generation, with privacy caveats around sending career assessment data and identifiers to the provider.

Before installing, be aware that roadmap requests may send your career goals, skills, experience, sessionId, timestamp, and optional userId to the provider's hosted API. Avoid including unnecessary personal or sensitive information unless you are comfortable with the provider handling it.

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
94% confidence
Finding

The skill documentation instructs users to include persistent identifiers such as sessionId and optional userId, but it provides no notice about privacy handling, retention, sharing, or minimization. This can lead users or integrating agents to transmit linkable personal or behavioral data to a third-party service without informed consent or safeguards, increasing privacy and compliance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
81% confidence
Finding

The skill directs traffic to an external API endpoint, which means user-supplied assessment data, session identifiers, and potentially user identifiers are transmitted outside the local trust boundary. In this skill's context, the danger is elevated because the transmitted payload includes profiling-related career data plus tracking identifiers, yet the skill provides no trust, privacy, or security assurances about the remote service.

Content

Scanner excerpt · SKILL.md (reported line 232)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/quantum-tech
- **API Docs:** https://api.mkkpro.com:8070/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The schema collects sessionId, timestamp, and optional userId, but the API spec provides no notice about purpose, retention, sharing, or minimization of this data. In a career-guidance context, these identifiers can enable tracking or linkage of user activity, creating privacy and compliance risk if users or integrators are not properly informed.

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-style file, so vague-trigger review applies. The description "Generate personalized quantum technology roadmap" states a capability but provides no constraints, activation conditions, or exclusions, which can make the skill appear applicable to a wide range of generic career-guidance requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.