ClawHub
Back to skill

Security audit

Social Media Mgmt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward API description for generating social media management career roadmaps, with privacy notes around external API use but no evidence of hidden, persistent, destructive, or deceptive behavior.

Before installing, treat this as a third-party API integration: only submit assessment details and identifiers you are comfortable sending to the provider, prefer pseudonymous session IDs, and review the provider's privacy and retention practices if using it with real users.

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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill directs users to an external API endpoint, which means any submitted assessment data, session IDs, timestamps, and optional user IDs may be transmitted outside the local environment. In this context, the danger is not obviously malicious, but the skill does not disclose trust boundaries, data handling practices, or security expectations for the external service, creating a real exfiltration and privacy risk.

Content

Scanner excerpt · SKILL.md (reported line 193)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/social-media-mgmt
- **API Docs:** https://api.mkkpro.com:8188/docs

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The sample request explicitly includes session identifiers, user IDs, and timestamps, but the skill provides no warning about collecting, transmitting, or handling user-related data. While these fields are common in APIs, omitting privacy and data-handling guidance can lead integrators to send trackable identifiers to a third-party service without informed consent or minimization.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This OpenAPI file is a manifest/config-style file, so vague-trigger checks apply. The endpoint summary and description say only 'Generate Roadmap' and 'Generate personalized Social Media Management roadmap' without clarifying trigger scope, input conditions, or exclusions, which is broad enough to overlap with many generic roadmap-generation requests.

Content

No source excerpt is available for this finding.