Security audit

新闻早报

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed news-hotspot fetcher with optional user-approved scheduling, though users should review the cron command before running it.

Install only if you want a Chinese-language hotspot/news fetcher that contacts hotspot.api4claw.com. Leave it in default mode for read-only use. If enabling scheduled delivery, inspect the generated cron command, ensure the destination values are normal trusted identifiers, and avoid running a shell command with unexpected characters in --channel or --to.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:35
Finding: Shell Command Injection Through Unsanitized Cron Delivery Arguments
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
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 (6)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.
md
- 接收 cron 的 OpenClaw agent **须能加载本 skill**（同一项目中的 `SKILL.md` / 规则包）。若定时环境无本 skill，须在 `--message` 中内联完整 URL 与 Output Rules 要点。

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.
md
### Prerequisites for scheduled runs - 接收 cron 的 OpenClaw agent **须能加载本 skill**（同一项目中的 `SKILL.md` / 规则包）。若定时环境无本 skill，须在 `--message` 中内联完整 URL 与 Output Rules 要点。 - 修改 `--cron` / `--tz` 时保持 `--message` 明确为 **hotspots consumer** 拉取，避免与其它定时报告混淆。 ## Scheduled runs（定时触发时）

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.
md
### Prerequisites for scheduled runs - 接收 cron 的 OpenClaw agent **须能加载本 skill**（同一项目中的 `SKILL.md` / 规则包）。若定时环境无本 skill，须在 `--message` 中内联完整 URL 与 Output Rules 要点。 - 修改 `--cron` / `--tz` 时保持 `--message` 明确为 **hotspots consumer** 拉取，避免与其它定时报告混淆。 ## Scheduled runs（定时触发时）

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · SKILL.md (reported line 138)May include surrounding context.
md
### Prerequisites for scheduled runs - 接收 cron 的 OpenClaw agent **须能加载本 skill**（同一项目中的 `SKILL.md` / 规则包）。若定时环境无本 skill，须在 `--message` 中内联完整 URL 与 Output Rules 要点。 - 修改 `--cron` / `--tz` 时保持 `--message` 明确为 **hotspots consumer** 拉取，避免与其它定时报告混淆。 ## Scheduled runs（定时触发时）

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The listed trigger words include "今日热点" and especially "早报", which are common, generic phrases that can appear in ordinary conversation and may cause unintended activation. The description does not provide exclusion conditions, narrow context constraints, or negative examples to clarify when the skill should or should not activate.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The default prompt template hard-codes a daily schedule at 09:30 in Asia/Shanghai, and later workflow instructions repeatedly require Beijing time. This imposes a specific locale/timezone behavior without offering user choice or documenting a justified region-specific limitation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.