Back to skill

Security audit

news-collector

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent newsletter-generation skill with disclosed web collection and optional recurring brief workflows, with no code, installer, hidden persistence, or credential handling found.

Before enabling periodic mode, confirm the sources, frequency, delivery channel, and whether the agent should save source lists or collected items. Expect the skill to browse external sites for the topics you configure.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly supports periodic brief delivery, but it does not disclose how ongoing collection and push behavior works, what delivery channel is used, or what data may be retained between runs. In an agent setting, undisclosed recurring behavior can surprise users, create privacy issues, and lead to continued outbound actions or notifications without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to collect information from websites, blogs, RSS, and social media, but it does not clearly warn the user that external services will be contacted. This can expose user interests or configured topics to third parties, trigger unexpected network activity, and create trust/privacy issues if users believe processing is local-only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown template uses Chinese headings and placeholders throughout, with no indication that language selection is optional. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown template uses Chinese labels and placeholders throughout, such as 日期, 可选栏目, 扩展阅读, 来源, and 摘要, but does not indicate that the skill is intentionally limited to Chinese-language use. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.