Back to skill

Security audit

knowledge-base-qa-assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward document Q&A knowledge-base guide, with expected document upload, indexing, retrieval, and deletion behavior disclosed in the artifact.

Before installing, treat uploaded files as retained and searchable knowledge-base content. Avoid sensitive documents unless you know who can query the knowledge base, how indexed content is isolated, and how deletion or recovery works.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill encourages users to upload private documents into a retrievable knowledge base, but it does not clearly disclose that content will be stored, indexed, and potentially surfaced later in answers. In an enterprise or sensitive-document context, this can lead to unintentional retention and secondary disclosure of confidential data to future users or sessions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documented single-document deletion command lacks an explicit confirmation or safeguard, increasing the risk of accidental or unauthorized data loss. In a shared knowledge-base workflow, a mistaken filename or misuse of the command could remove important indexed content without a recovery checkpoint.

Content

No source excerpt is available for this finding.