ClawHub
Back to skill

Security audit

Veterinary Science

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its stated career-roadmap purpose, but it sends profile-like career data and tracking identifiers to an external service without clear privacy or retention disclosure.

Install only if you are comfortable sending veterinary career assessment details, goals, session identifiers, timestamps, and any supplied userId to the provider's external API. Avoid submitting unnecessary personal details until the provider documents privacy, retention, deletion, and data-sharing practices.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation states that the platform analyzes assessment data, experience, skills, and professional objectives, which are user profiling inputs, but it provides no privacy notice, retention policy, or data-handling warning. This creates a real risk that users or integrators will transmit personal and behavioral data to an external service without informed consent or understanding of downstream use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example request explicitly includes a sessionId, userId, and timestamp, which are tracking and correlating identifiers, but there is no warning that these values are sent to a third-party service. Even if not directly sensitive alone, they enable cross-session linkage and user profiling when combined with career goals and skills data.

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 219)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/veterinary-science
- **API Docs:** https://api.mkkpro.com:8189/docs

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill claims to be a veterinary career-roadmap service, but the provider metadata advertises '200+ security APIs' and unrelated platforms. This domain mismatch is a trust and provenance problem: users may be induced to send career assessment and tracking data to a service whose actual purpose, controls, or operator identity are unclear.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This manifest file defines a request body containing assessment data, sessionId, timestamp, and optional userId for the roadmap-generation endpoint, but the API description provides no user-facing warning or disclosure about collecting and transmitting this data. For manifest files, missing-warning issues are relevant when markdown descriptions are absent and the interface omits notice about behaviors that could affect user privacy.

Content

No source excerpt is available for this finding.