Back to skill

Security audit

Daily News

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple daily-news helper that calls a disclosed third-party news API and does not install persistence, request credentials, or run hidden code.

Install this only if you are comfortable sending news category and subcategory requests, along with normal network metadata such as IP address and timing, to the 6551 API. No credentials are required, and the inspected artifact does not show hidden code or persistence.

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 (2)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructs the agent to make unauthenticated requests to a third-party service without any user-facing disclosure or consent language. This can expose user metadata such as IP address, request timing, and query content to an external provider, which is a real privacy and trust issue even if the endpoint itself appears benign.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
61% confidence
Finding

The response example highlights English-oriented fields such as summary_en and presents the skill entirely in English, while also exposing multilingual content fields. Because the file does not state whether users may choose their preferred language or locale, it may conflict with a policy requiring language choice rather than a fixed default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.