ClawHub

Miniflux

Security checks across malware telemetry and agentic risk

Overview

This Miniflux skill is coherent and purpose-aligned, but users should treat it as a write-capable RSS account integration and verify the helper binary before use.

Before installing, verify the openclaw-miniflux-mcp binary source or prefer Cargo installation, use a dedicated Miniflux API token, store credentials only in local MCP config, and run with --read-only if you only want browsing and reading rather than feed/category changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The skill description is broadly phrased around many user requests without clearly defining tighter activation boundaries or requiring explicit Miniflux-related context. In an agentic system, this can cause overbroad invocation and unintended access to a user's RSS data or trigger follow-on write-capable workflows when a request is only loosely related.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises create, update, delete, import, mark-as-read, and bookmark-changing capabilities without an upfront warning that these operations modify persistent user data. In practice, this increases the chance an agent will perform destructive or state-changing actions—such as deleting feeds, renaming categories, or bulk marking entries as read—without the user appreciating the consequences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal