Back to skill

Security audit

Intel Briefing

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly a news briefing generator, but its package includes under-disclosed recurring main-session scheduling and broad memory/file side effects that users should review before installing.

Review this skill carefully before installing. Use it only if you are comfortable with news searches, reading and updating agent notes, saving local HTML files, and possible QQ bot media export. Do not enable the bundled cron setup unless you intentionally want recurring unattended runs, and prefer a dedicated restricted session instead of the main session. Verify any optional skill dependencies by publisher, version, and digest before installing them.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T06 · System Persistence

Error
Location
CRON_SETUP.md:37
Finding

Undisclosed Recurring Execution Through Scheduled Main-Session Events

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:123
Finding

Overbroad Access to Long-Term Agent Memory

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:439
Finding

Unpinned Installation of Third-Party Skills

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (18)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description emphasizes a manually triggered briefing generation system with data processing and HTML output. The provided code chunk does not perform briefing generation at all; instead, it prepares a directory and outputs instructions to configure three recurring cron jobs. The strongest mismatch is that the description says manual trigger, while the code is specifically about automated scheduled execution. Although morning/noon/evening briefings are thematically related, this chunk's primary behavior is cron setup, which is an undeclared operational capability and materially different from the declared purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation enables unattended scheduled execution even though the skill metadata says it is manually triggered. That mismatch can cause the skill to run without an explicit user action, increasing the chance of unexpected data collection, briefing generation, and file writes on a recurring basis.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

The cron commands explicitly bind recurring executions to '--session main', creating persistence in a shared long-lived session context. Scheduled actions in a persistent session can inherit prior state, credentials, or conversation context, increasing the risk of unintended access, cross-task data leakage, or repeated actions with stale authorization.

Content

Scanner excerpt · CRON_SETUP.md (reported line 37)May include surrounding context.

bash
# 早间简报
openclaw cron create \
  --name intel-briefing-morning \
  --cron "0 7 * * *" \
  --system-event "EXECUTE_INTEL_BRIEFING_MORNING" \

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The listed trigger phrases are common natural-language terms such as '早报', '晚报', and 'daily briefing', which may appear in ordinary conversation. Overly broad activation phrases can cause accidental execution of the skill, leading to unintended network activity or local file generation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad everyday phrases such as '早报', '午报', '晚报', and '生成简报', which can cause accidental activation during normal conversation. Because the skill performs side effects like reading memory, writing notes, and saving files, overbroad invocation increases the chance of unintended data access and modification without a deliberate user request.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

At L016 and L027-L032, the document says the skill does not rely on external CLI tools or extra packages and is designed for zero external dependencies. However, L041-L043 and L431 instruct installing web-search and ai-news-collectors skills with clawhub install, which directly contradicts the earlier dependency-free claim.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
79% confidence
Finding

The document states that Chinese search quality is preferred and the skill description, trigger phrases, and operational guidance are centered on Chinese-language use without offering a user language choice. This creates a natural-language locale preference that is not explicitly optional or justified as a region-specific tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill directs automatic reads from daily notes and long-term memory and writes back via edit_daily, but does not provide a clear user-facing warning or consent gate for modifying stored notes. In context, this is more dangerous because the notes are used as execution state, so accidental invocation could expose or alter personal memory artifacts beyond the immediate briefing task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill saves archive files, overwrites a latest-version HTML file, and may additionally copy files into a QQ media directory, all without an explicit upfront warning about file creation or overwrite behavior. This is risky because ambiguous triggering or unattended execution can modify local state and bot-ingestion paths in ways the user did not intend.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs copying generated HTML into a channel-specific QQ bot media directory, which extends behavior from content generation into filesystem manipulation and outbound delivery preparation. This creates risk of unintended file writes, overwrites, or misuse of a privileged bot-consumed path, especially because the action is automatic and tied to channel detection rather than explicit user confirmation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The entire skill file is written exclusively in Chinese and provides no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the regional constraint is clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The HTML root declares lang="zh-CN", indicating the skill output is fixed to Simplified Chinese. Under the policy, forcing a specific language/locale without user opt-in is a natural-language policy violation unless the locale limitation is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

All user-facing comments and echoed instructions in the script are written in Chinese, which imposes a specific language on users without any opt-in or indication that the skill is region-specific. This matches the policy category for language or locale constraints that are not optional or justified.

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 · setup-cron.sh (reported line 5)May include surrounding context.

sh
# 简报系统定时任务配置脚本

# 确保 download 目录存在
mkdir -p ~/my-project/download

# 输出配置说明
echo "=========================================="

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

All user-facing instructions in this file are presented in Chinese, with no indication that the skill supports alternative languages or that Chinese is a justified locale-specific requirement. This may violate language-choice policy if the broader skill is intended for general users.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The document states that generated HTML files will be written to a local download directory, but the skill description does not prominently warn users of this side effect. Silent local writes can expose sensitive content to other local users, backups, sync tools, or later accidental sharing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents the version history only in Chinese, and there is no visible note that the language is optional, user-selectable, or justified as a region-specific constraint. 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
91% confidence
Finding

The entire skill reference is written only in Chinese, and there is no indication that language selection is optional or that the document is intended exclusively for a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user opt-in can constitute a natural-language policy violation.

Content

No source excerpt is available for this finding.