ClawHub
Back to skill

Security audit

ai-news-digest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent AI news digest template; its email and credential examples need care, but I found no hidden, destructive, or deceptive behavior.

Install only if you are comfortable configuring any future live-news, OpenAI, and SMTP integrations yourself. Use scoped or app-specific mail credentials, avoid putting secrets in shared shell history or checked-in files, and review any cron job before enabling automated email delivery.

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
  • 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
Confidence
89% confidence
Finding
The skill advertises email sending and automated delivery but does not warn users that generated summaries and recipient addresses will be transmitted through external SMTP infrastructure. This can lead to unintentional disclosure of sensitive content or personal data, especially when users automate daily digests without understanding where data is sent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs users to place SMTP credentials in environment variables, including a plaintext password, without guidance on secure secret handling. This increases the risk of credential exposure through shell history, shared environments, logs, screenshots, or accidental publication, which could enable unauthorized email account access or abuse.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The manifest description is written entirely in Chinese and states the skill will automatically fetch and summarize AI and technology news into digests, with no indication that language is selectable. This creates a natural-language locale policy concern because it appears to assume or enforce Chinese-language use without user opt-in or a documented region-specific justification.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The natural-language instructions and examples are effectively constrained to Chinese, and the file does not indicate that users may choose another language or that the skill is intentionally region-specific. Under the stated policy, forcing a specific language without opt-in can be a locale-policy issue.

Static analysis

No suspicious patterns detected.