ClawHub
Back to skill

Security audit

Forensic Audit Roadmap

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent external API integration for generating forensic-audit career roadmaps, with privacy considerations users should understand before submitting profile details.

Before installing, treat this as a third-party API service: avoid entering confidential employer data, client names, investigation details, or unnecessary personal identifiers, and use the optional userId only if persistent profile tracking is actually needed. The package itself does not show local execution or persistence, but the publisher should ideally add clear privacy, retention, and deletion terms.

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
93% confidence
Finding

The skill explicitly collects persistent identifiers (sessionId, optional userId) alongside detailed professional assessment data, but provides no privacy notice, retention policy, sharing disclosure, or guidance on minimizing sensitive input. This creates unnecessary privacy risk because users may submit identifiable career-profile data without informed consent or understanding of how it is stored, linked, or transmitted.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
78% confidence
Finding

The skill directs users to transmit assessment data to an external domain (api.mkkpro.com), which means career-profile and identifier data leaves the local trust boundary. While external APIs are expected for this type of skill, the danger is increased here because the documentation does not disclose security controls, data processing terms, or privacy assurances for the third-party service.

Content

Scanner excerpt · SKILL.md (reported line 206)May include surrounding context.

md
# References

- **Kong Route:** https://api.mkkpro.com/compliance/forensic-audit
- **API Docs:** https://api.mkkpro.com:8114/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This is a manifest/config file, so vague-trigger review applies. The operation is described only in broad natural language such as "Generate Roadmap" and "Generate personalized forensic audit roadmap," without any narrowing conditions, explicit trigger phrases, or exclusions, which can make invocation matching overly broad in agent environments that rely on manifest text.

Content

No source excerpt is available for this finding.