ClawHub
Back to skill

Security audit

Readwise & Reader

Security checks for vulnerabilities and agentic risk

Overview

This Readwise skill is a straightforward, disclosed integration for reading highlights and Reader documents, with a user-invoked URL save command.

Install this only if you are comfortable giving the skill access to your Readwise account data. Treat returned highlights, notes, saved article metadata, and partial content as potentially sensitive, and use the save command only for URLs you intend to add to Reader.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill description says it provides access to Readwise highlights and saved articles, but the CLI also supports a `save` command that creates new Reader entries from arbitrary URLs. This is a scope-expansion issue: users or calling agents may grant the skill read-oriented access while unknowingly enabling write actions against the connected Readwise account.

Description-Behavior Mismatch

Low
Confidence
84% confidence
Finding
The `get` path returns full document details including `content`, `notes`, and `highlights`, which goes beyond a narrow interpretation of 'highlights and saved articles' access. While this is not code execution or direct token leakage, it increases data exposure and can surprise users who expect more limited retrieval behavior.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill instructs users to configure a persistent Readwise API token and then use commands that fetch, search, export, and save data against external Readwise/Reader services, but it does not clearly warn that the user's highlights, saved articles, queries, and submitted URLs will be transmitted to that third-party service. This is primarily a transparency and informed-consent issue rather than an exploit primitive, but it can expose sensitive reading history or notes if users do not realize external data transfer is occurring.

Static analysis

No suspicious patterns detected.