ClawHub

Flomo Random Walk

Security checks across malware telemetry and agentic risk

Overview

The skill’s Flomo note-walking feature is coherent, but it exposes a Flomo API token directly in the public instructions.

Do not install this version as-is unless the exposed Flomo token has been removed and rotated. A safer version should require each user to provide their own Flomo credential through a protected secret or environment variable, and users should be comfortable with note contents, note IDs, tags, and walk history being visible to the agent and stored locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

High
Confidence
99% confidence
Finding
The skill embeds a live-looking API token directly in documentation and explicitly instructs reading credentials from SECRET.md. Hard-coded secrets are highly sensitive because they can be copied, reused, or harvested by anyone with access to the skill file, enabling unauthorized access to the user's flomo data and any actions permitted by that token.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill persists a user's walk history, including note IDs, tags, and usage patterns, without clearly informing the user or obtaining consent. Silent retention of activity history increases privacy risk, especially for personal knowledge bases where IDs, tags, and traversal paths can reveal sensitive interests, projects, or mental-state patterns over time.

Missing User Warnings

Medium
Confidence
80% confidence
Finding
The skill sends note identifiers and retrieves note content from an external service but does not provide a user-facing privacy notice or consent boundary. In a note-exploration context, these requests may expose sensitive personal content or metadata to a third-party endpoint, making the lack of transparency and consent materially risky.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal