ClawHub
Back to skill

Security audit

IOT Developer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward external API guide for generating IoT career roadmaps, with privacy considerations around the assessment data it sends but no hidden execution, persistence, or destructive behavior.

Before installing, confirm you are comfortable sending assessment details to the listed external API. Prefer pseudonymous session IDs, omit userId unless needed, and avoid submitting sensitive employment or personal details beyond what is necessary for the roadmap.

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
91% confidence
Finding

The sample request includes persistent identifiers such as sessionId, userId, timestamps, prior roles, skills, and career goals, which together can constitute personal or behavioral data. Presenting these fields without any privacy notice, minimization guidance, retention policy, or consent language increases the risk that integrators will transmit unnecessary user data to a third-party service without adequate safeguards.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
76% confidence
Finding

The skill references an external API endpoint, which means user-supplied assessment data may be transmitted outside the local trust boundary to a third-party domain. In this skill's context, the transmitted content includes user identifiers and profiling-style career data, making the external transmission more sensitive and increasing privacy and data governance risk.

Content

Scanner excerpt · SKILL.md (reported line 218)May include surrounding context.

md
## References

- Kong Route: https://api.mkkpro.com/career/iot-developer
- API Docs: https://api.mkkpro.com:8098/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This JSON manifest-like API spec defines a roadmap-generation request that accepts assessment data, session identifiers, timestamps, and an optional user ID, but it does not describe any constraints on when this capability should be invoked or what requests are out of scope. For manifest/config-style files, the absence of specificity around invocation scope can make activation or use conditions overly broad.

Content

No source excerpt is available for this finding.