ClawHub
Back to skill

Security audit

Flashrev Mailer Notion Tracker

Security checks across malware telemetry and agentic risk

Overview

This skill transparently syncs FlashRev email send logs into a user-selected Notion database, with sensitive data handling that is disclosed and aligned with its stated purpose.

Install only if you are comfortable sending FlashRev outreach metadata and up to 300 characters of each email body into the configured Notion database. Use query-only mode when you only want to inspect existing records, and restrict the Notion integration to the intended database.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill is designed to push email content and metadata into Notion, including recipient email, subject, body preview, sender mailbox, timestamps, and error details, but the description does not clearly warn users that this data is transmitted to and stored in a third-party service. This omission can cause unintentional disclosure of sensitive outreach data, personal data, or confidential campaign information.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest uses broad trigger language such as 'whenever emails are sent or dry-run previewed' and 'also use when the user asks to check what emails were sent,' which increases the chance the skill is auto-invoked in situations the user did not intend. Because invocation causes access to send logs and can write email metadata to Notion, overbroad triggering raises the risk of unnecessary external data transfer and persistence.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.