ClawHub
Back to skill

Security audit

News

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local personalized-news helper, and the reviewed artifact does not instruct external data sending, hidden execution, or unsafe persistence.

Before installing, be comfortable with the skill keeping local news preferences and engagement history in ~/news/. Review or delete those files if you do not want ongoing personalization. The package reviewed here does not include executable code or instructions to send that data elsewhere.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

md
- Engagement history in `~/news/history.md`

**This skill does NOT:**
- Send data to external services
- Access files outside `~/news/`
- Store news content permanently

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation guidance is broad enough that an agent may invoke this skill whenever a user asks for news-like content, without clear boundaries around when memory access or profile building should occur. While not directly malicious, overly permissive triggering increases the chance of unnecessary collection and use of local preference/history data in contexts the user did not explicitly intend.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

md
- Engagement history in `~/news/history.md`

**This skill does NOT:**
- Send data to external services
- Access files outside `~/news/`
- Store news content permanently

Static analysis

No suspicious patterns detected.