ClawHub
Back to skill

Security audit

Outlook Inbox

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent Outlook purpose, but it asks users to install and authorize a third-party ClawLink plugin with broad Microsoft account access without a pinned or verifiable plugin version.

Review the ClawLink plugin and OAuth consent carefully before installing. Use a limited Microsoft account if possible, confirm every send/delete/rule/calendar write action, and know how to revoke the Microsoft connected app and remove the plugin if you no longer need it.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Error
Location
SKILL.md:47
Finding

Unpinned Third-Party Plugin with Broad OAuth-Backed Account Access

Content
View full analysis
Remediation
View remediation

SkillSpector

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)

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 172)May include surrounding context.

md
| Tool | Description | Mode |
|------|-------------|------|
| `outlook_add_mail_attachment` | Add an attachment to a message | Write |
| `outlook_create_attachment_upload_session` | Create an upload session for large attachments (>3 MB) | Write |
| `outlook_list_attachments` | List attachments on a message | Read |

### Rules & Categories

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 302)May include surrounding context.

md
| Tool | Description | Mode |
|------|-------------|------|
| `outlook_add_mail_attachment` | Add an attachment to a message | Write |
| `outlook_create_attachment_upload_session` | Create an upload session for large attachments (>3 MB) | Write |
| `outlook_list_attachments` | List attachments on a message | Read |

### Rules & Categories

Static analysis

No suspicious patterns detected.