Back to skill

Security audit

Japanese News Briefing 日本語でニュースまとめ

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Japanese news briefing skill that uses scheduled/manual prompts and web/weather sources without hidden code, credential access, or destructive behavior.

Install this only if you want a Japanese-language scheduled briefing that may perform web searches and weather lookups four times daily. Review your HEARTBEAT.md schedule so it runs only at the times and topics you intend.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README states that briefings are delivered in Japanese, and later configuration examples reinforce 'Japanese for all 4 briefings' as a fixed requirement. This is a natural-language locale policy issue because the skill appears to mandate a specific language rather than offering a user-selectable language or documenting a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 39)May include surrounding context.

または手動インストール:

bash
mkdir -p ~/.openclaw/skills/japanese-news-briefing
cd ~/.openclaw/skills/japanese-news-briefing
# SKILL.md と clawhub.json を配置

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The sample HEARTBEAT.md configuration explicitly sets 'Language: Japanese for all 4 briefings' and does not present this as a user choice. That wording reinforces a fixed-language policy that can violate locale-choice expectations unless the skill is clearly documented as intentionally Japanese-only.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This manifest describes the skill as providing 'automatic news briefings 4 times a day' but does not specify what event, schedule mechanism, or context causes the skill to run. For a manifest file, that ambiguity can create overly broad or unclear invocation expectations because users cannot tell when the skill activates versus when it does not.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest sets the skill language to 'ja', and the description also states the briefing is in Japanese, but there is no indication that users can choose a language or that the Japanese-only restriction is a documented regional requirement. This matches the policy concern for language or locale constraints imposed without user opt-in.

Content

No source excerpt is available for this finding.