ClawHub

Instapaper

Security checks across malware telemetry and agentic risk

Overview

This plugin coherently wraps Instapaper's CLI to manage a user's reading list, with the main caution being that delete tools can permanently remove Instapaper data when invoked.

Install only if you want your agent to manage your Instapaper account through instapaper-cli. Be careful with delete requests: confirm bookmark IDs or folder names first, prefer archive for reversible cleanup, and store Instapaper credentials through OpenClaw's sensitive config or SecretRef mechanisms rather than plaintext where possible.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The handler performs an irreversible bookmark deletion by always passing the force flag (`-yes-really-delete`) and exposes no confirmation or safeguard at this layer. In an agent skill context, this increases the chance of accidental or prompt-induced destructive actions because a mistaken tool invocation immediately deletes user data.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The folder deletion handler forces confirmation with `-yes` and does not provide any visible warning or secondary check before deleting a folder. In a tool-driven agent environment, this is risky because natural-language misunderstandings or malicious prompt manipulation can trigger destructive actions without giving the user a chance to stop them.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill exposes permanently destructive operations such as deleting bookmarks and deleting folders, but provides no warning, confirmation guidance, or distinction between reversible and irreversible actions. In an agent setting, this increases the chance that a model will invoke destructive tools from ambiguous user requests or as part of an over-broad workflow, causing unintended data loss in the user's Instapaper account.

VirusTotal

62/62 vendors flagged this plugin as clean.

View on VirusTotal