ClawHub
Back to skill

Security audit

PDF Summarizer

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it uploads a user-provided PDF to an external summarization API and returns a summary, with no bundled code, persistence, or hidden local access.

Install only if you are comfortable sending chosen PDFs to the external api.mkkpro.com service. Avoid uploading confidential contracts, personal records, medical/legal files, or proprietary business documents unless you have reviewed the provider's privacy, retention, and deletion 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
  • 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
Confidence
96% confidence
Finding
The skill encourages users to upload full PDF documents to a third-party API but does not warn that documents may contain sensitive, proprietary, legal, medical, or personal data. This omission can lead users to transmit confidential content off-platform without informed consent, creating privacy, compliance, and data-handling risk.

External Transmission

Medium
Category
Data Exfiltration
Content
## References

- **Kong Route:** `https://api.mkkpro.com/creative/pdf-summarizer`
- **API Docs:** `https://api.mkkpro.com:8000/docs`
Confidence
91% confidence
Finding
The skill routes user-supplied PDF content to an external domain, which means document contents leave the local trust boundary and are exposed to the security posture, logging, retention, and access controls of that third-party service. In this context, the danger is elevated because the advertised use cases include contracts, research papers, and enterprise documents, which commonly contain sensitive information.

Natural-Language Policy Violations

Low
Confidence
0% confidence
Finding
No natural-language language or locale policy violation is present in this file.

Vague Triggers

Low
Confidence
84% confidence
Finding
This is a manifest/config-style file, so vague-trigger checks apply. The specification exposes a generic '/summarize-pdf' operation and summary text, but provides no description of when this skill should or should not be invoked, no constrained trigger phrases, and no negative examples to prevent overly broad activation for any request involving PDFs or summarization.

Static analysis

No suspicious patterns detected.