ClawHub
Back to skill

Security audit

Nutrition Dietetics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward career-roadmap API integration, with the main caution that users may send professional profile data and identifiers to an external service.

Before installing, users should avoid submitting unnecessary personal identifiers, use fictitious or minimized session/user IDs where possible, and review the provider's privacy and retention practices for the external API.

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
89% confidence
Finding

The skill documentation includes example payloads containing user and session identifiers plus detailed assessment data, but provides no privacy notice, retention policy, minimization guidance, or warning against using real personal data. In a career-guidance context, this can normalize sending identifiable or sensitive professional profiling data to a third-party API and increases the risk of accidental exposure, logging, or noncompliant handling.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
78% confidence
Finding

The skill directs users to an external API endpoint, which causes user-supplied assessment data and identifiers to be transmitted outside the local environment to a third-party service. External transmission is not inherently malicious, but without explicit trust, security, and privacy guarantees, it creates data exposure, dependency, and supply-chain risk—especially because the skill handles personalized profile information.

Content

Scanner excerpt · SKILL.md (reported line 314)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/nutrition-dietetics
- **API Docs:** https://api.mkkpro.com:8181/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The POST /api/nutrition/roadmap operation accepts structured assessment data along with sessionId, timestamp, and optional userId, which indicates potentially sensitive user data is sent to a backend service. In this manifest file, there is no warning or disclosure in the endpoint description about sending user-provided assessment information or identifiers.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This manifest-style OpenAPI file defines the skill's primary action as 'Generate Roadmap' with a broad description of generating a personalized roadmap, but it does not document any specific invocation phrases, scope limits, or negative examples. In a manifest/config context, that ambiguity can make activation boundaries unclear and increase the risk of unintended invocation.

Content

No source excerpt is available for this finding.