Security audit

Instapaper

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Instapaper, but it can permanently delete account content through forced CLI options without explicit confirmation guidance in the skill instructions.

Install only if you are comfortable giving the agent access to your Instapaper account through instapaper-cli. Before using delete or folder-delete actions, require the agent to restate the exact bookmark ID or folder name and get explicit confirmation, because deletion may be permanent or move content unexpectedly.

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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 (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill documents permanently destructive operations such as `instapaper_delete` and folder deletion without requiring confirmation, warning about irreversibility, or advising the agent to verify user intent before execution. In an agent setting, this increases the chance of accidental data loss from ambiguous prompts, mis-clicked tool calls, or prompt injection that causes the assistant to invoke deletion actions on the user's behalf.

Static analysis

No suspicious patterns detected.