Back to skill

Security audit

Knowledge Capture

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Notion documentation helper, but users should treat captured conversations as data that will be stored in Notion.

Install only if you intend to send selected conversation notes or transcripts to Notion. Use a least-privilege Notion integration token, verify the target database/workspace, and avoid using it with secrets, regulated data, or confidential conversations unless you are authorized to store that content in Notion.

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
95% confidence
Finding

The skill requests a Notion API token and references a third-party integration, but it provides no guidance on secure credential handling or the privacy implications of sending captured content to Notion. This increases the risk of token exposure, overbroad permissions, and unintentional transmission of sensitive data to an external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly describes creating or updating Notion documents from conversation content, but it does not clearly warn users that their input will be transmitted to and persisted in a third-party workspace. This can lead to accidental disclosure of sensitive meeting notes, transcripts, or personal data when users assume the transformation is local or read-only.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.