ClawHub
Back to skill

Security audit

System Administrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed career-roadmap API integration, with privacy considerations because it sends assessment data and identifiers to an external service.

Before installing, treat this as a third-party API integration: avoid sending unnecessary personal identifiers, use opaque session IDs where possible, and review the provider's privacy and retention terms if real user assessment data will be submitted.

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
87% confidence
Finding

The skill explicitly documents collection of user assessment data, session identifiers, timestamps, and optional user IDs, but provides no privacy notice, data minimization guidance, retention limits, or handling constraints. In a career-assessment context this metadata can enable tracking, profiling, and correlation of individuals, increasing privacy and compliance risk if consumers send real user data to the external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
74% confidence
Finding

The skill directs users to an external API endpoint, which means assessment data and identifiers described elsewhere in the document may be transmitted to a third-party service outside the local trust boundary. While external endpoints are expected for API skills, the combination of user profiling data plus undisclosed handling practices makes this a real security and privacy concern rather than a standalone false positive.

Content

Scanner excerpt · SKILL.md (reported line 205)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/system-administrator
- **API Docs:** https://api.mkkpro.com:8051/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The request schema explicitly accepts sessionId and userId values, but the spec provides no disclosure, minimization guidance, or indication of how these identifiers are protected in transit and use. In a career-roadmap skill handling assessment data, collecting linkable identifiers without clear user-facing transparency increases privacy risk and can enable unnecessary tracking or correlation if exposed or misused.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This is a manifest-style OpenAPI file, so vague-trigger checks apply. The only operation is broadly described as "Generate Roadmap" without any natural-language constraints, activation conditions, or exclusion examples, making it unclear what exact user intents should map to this skill versus other roadmap or career-planning requests.

Content

No source excerpt is available for this finding.