Back to skill

Security audit

ME Event 精选

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward ME News event reminder that uses fixed read-only API endpoints and a local state file for user-approved subscriptions.

Install this only if you want ME News event reminders, are comfortable with recurring requests to api.me.news, and confirm the delivery destination and schedule. Keep channel tokens out of the skill directory and state file, and use the documented pause or unsubscribe flow if you no longer want reminders.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Rogue AgentSelf-Modification, Session Persistence
Findings (18)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · scripts/record-delivery.mjs (reported line 22)May include surrounding context.

js
state.recent_ids = pending.recent_ids || state.recent_ids || [];
    state.last_delivery_status = 'success';
    state.last_delivered_at = new Date().toISOString();
    delete state.pending_delivery;
  } else {
    pending.failure_count = (pending.failure_count || 0) + 1;
    pending.last_failure_at = new Date().toISOString();

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructions and user-facing phrasing are written entirely in Chinese, including required output labels and message-format guidance. There is no indication that the user can opt into another language, which can violate a language/locale policy when the skill is used in broader contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The format specification requires fixed Chinese headings and labels such as "今日开始", "明日开始", and "新增会议", and line L36 further fixes a locale-specific rendering style. This imposes a specific language/locale in the skill output without indicating that the user can choose or opt into that language.

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 · references/agent-compatibility.md (reported line 22)May include surrounding context.

md
- Non-zero exit means failure. Surface the stderr summary and do not claim success.
- After non-empty poll output is delivered, record `success` only when the delivery tool confirms success. Record `failed` on a confirmed failure. An unknown result must remain pending and be retried.
- `daily-upcoming.mjs` does not advance the changes cursor and does not use delivery feedback.
- Never let two poll processes write the same state file concurrently.

## CLI validation

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The document instructs OpenClaw users to schedule a daily job at 10:00 in Asia/Shanghai, which imposes a specific locale/timezone choice in natural language. There is no nearby opt-in, user choice, or justification that this region-specific setting is required, so it appears to force a locale-specific behavior contrary to the policy.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
# ME Event Skill API

Base URL: `https://api.me.news/skill/events`

所有时间按 `Asia/Shanghai`(UTC+8)处理。成功响应的顶层 `code` 为 `200`。

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

md
# ME Event Skill API

Base URL: `https://api.me.news/skill/events`

所有时间按 `Asia/Shanghai`(UTC+8)处理。成功响应的顶层 `code` 为 `200`。

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/api.md (reported line 3)May include surrounding context.

md
# ME Event Skill API

Base URL: `https://api.me.news/skill/events`

所有时间按 `Asia/Shanghai`(UTC+8)处理。成功响应的顶层 `code` 为 `200`。

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib.mjs (reported line 4)May include surrounding context.

js
# ME Event Skill API

Base URL: `https://api.me.news/skill/events`

所有时间按 `Asia/Shanghai`(UTC+8)处理。成功响应的顶层 `code` 为 `200`。

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · sources.md (reported line 7)May include surrounding context.

md
# ME Event Skill API

Base URL: `https://api.me.news/skill/events`

所有时间按 `Asia/Shanghai`(UTC+8)处理。成功响应的顶层 `code` 为 `200`。

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · sources.md (reported line 8)May include surrounding context.

md
# ME Event Skill API

Base URL: `https://api.me.news/skill/events`

所有时间按 `Asia/Shanghai`(UTC+8)处理。成功响应的顶层 `code` 为 `200`。

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · sources.md (reported line 9)May include surrounding context.

md
# ME Event Skill API

Base URL: `https://api.me.news/skill/events`

所有时间按 `Asia/Shanghai`(UTC+8)处理。成功响应的顶层 `code` 为 `200`。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code emits multiple fixed Chinese strings in formatted event descriptions and warnings, such as the fallback location text and time labels. That enforces a specific language for user-visible output without any opt-in, choice, or documented region-specific justification in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code hard-codes Chinese-formatted date labels, warnings, titles, and descriptions in test assertions, which enforces a specific language/locale behavior. The file does not indicate any user opt-in or configurable locale selection, so it reflects a natural-language policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This markdown instructs agents to use and update a shared state file in the workspace, including recording delivery outcomes and preserving initialization state. Because the file describes persistent writes to user workspace data but does not explicitly warn that the skill will create and modify that file over time, it lacks a clear user-facing disclosure for a data-affecting behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

Line L05 states that all times are handled in Asia/Shanghai and the document is written as a universal requirement rather than an optional or region-specific mode. Under the policy, forcing a specific locale without user choice can be a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.