Security audit

今日热点

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches and displays public hotspot/trending content from a fixed API, with optional scheduled delivery only after user approval.

Before installing, be aware that it may suggest a daily cron job for hotspot updates; only approve that if you want scheduled messages. Ambiguous requests containing "热点" may trigger the skill, but its default behavior is read-only API fetching.

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

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 56)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 56)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_tophot 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 78)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_tophot 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 153)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_tophot 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: 96% confidence
Finding: The trigger phrase includes the single broad term "热点", which is highly ambiguous and can cause the skill to activate on many unrelated conversations. Over-broad activation increases the chance of unintended network access, irrelevant cron suggestions, or the skill taking control when the user did not specifically request this functionality.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The skill hard-codes Chinese-language prompts and trigger guidance without checking the user's preferred language. While not a classic security flaw, forced language can mislead users about what actions are being proposed, especially around cron setup, reducing informed consent and increasing the risk of accidental approval.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.