ClawHub
Back to skill

Security audit

Newsletter Digest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward newsletter and article summarizer with reading-list features, but users should be mindful that shared email/newsletter content and preferences may be processed.

Install only if you are comfortable sharing newsletter/email text and article links with the assistant. Treat any reading-list or preference-learning features as potentially retained state unless your environment clearly documents how to review or delete them.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases include generic requests such as "article summary," "reading list," and "what should I read," which can match normal assistant interactions unrelated to this specific skill. That creates a real risk of unintended activation, causing newsletter/inbox-processing behavior to run in contexts where the user did not clearly consent, especially given the skill handles forwarded emails, links, and preference learning.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises processing forwarded newsletters, linked articles, and learning user interests over time, but does not warn users that personal inbox content and behavioral preferences may be stored, analyzed, or retained. In this context, missing disclosure is security- and privacy-relevant because users may unknowingly expose sensitive email content, subscription habits, or inferred interests without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.