Back to skill

Security audit

归档

Security checks for vulnerabilities and agentic risk

Overview

The skill is a markdown-only Notion archive helper, but it asks for broad shell/file/search authority and advertises crawler-bypass and generic command use outside that stated purpose.

Review before installing. Use this only for clearly authorized Notion archive/export work, and avoid letting it run shell commands, crawl websites, bypass anti-crawling controls, or process unrelated local files unless you explicitly approve the exact action and data scope.

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is presented as a Notion archive/search/sync tool, but the documentation broadens it into generic file handling and command execution. This creates dangerous scope drift: an agent may invoke powerful local capabilities under a benign-seeming Notion task, increasing the chance of unintended filesystem access or shell execution.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The paid-feature table advertises anti-crawling bypass and parallel web crawling, which materially departs from a stated Notion archival purpose. Hidden or mismatched capabilities are risky because they normalize unauthorized scraping behavior and can cause the agent to perform actions outside user expectations.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Documenting generic system command execution for a Notion archive skill is unjustified and materially increases risk, because shell access can be repurposed for arbitrary local actions unrelated to the user task. In an agent environment with exec enabled, vague permission to run commands can lead to data exposure, destructive commands, or pivoting to other system resources.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file describes the skill as a Notion archive tool while also promoting web-crawling and anti-crawler bypass capabilities, creating a contradictory security posture. This mismatch can mislead reviewers and users about what the skill is allowed to do, making abusive or policy-violating behavior easier to hide behind a legitimate integration label.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The invocation guidance is overly broad and lacks precise activation boundaries, so the skill may be triggered for loosely related requests. When a skill exposes read/exec/grep/glob tools, ambiguous triggering increases the probability of overreach into sensitive files or unnecessary command execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The applicable-scope section is generic enough to cover broad data processing and search use cases beyond Notion archival. In context, that ambiguity is more dangerous because the skill also declares powerful tools, so an agent may apply it in contexts where its permissions exceed what the user intended.

Content

No source excerpt is available for this finding.