ClawHub
Back to skill

Security audit

Hacker News Daily Summary (Bilingual)

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public Hacker News items, translates titles with Baidu, writes a local report, and optionally posts that report to a user-configured Feishu webhook.

Install only if you are comfortable sending Hacker News titles to Baidu Translate and, if FEISHU_WEBHOOK is set, sending the generated report text to that Feishu webhook. Store the Baidu secret and webhook carefully, since putting them in ~/.bashrc keeps them on disk in plaintext.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The title and description specify a Chinese-oriented workflow (Chinese title generation and Chinese documentation) but do not indicate that language selection is optional or limited for a justified regional purpose. Under the stated policy, forcing a specific language or locale without user opt-in is a natural-language policy concern.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The script sends article titles to Baidu Translate via HTTP at L23, and later may send a portion of the generated report to Feishu at L68. While comments describe required environment variables and optional Feishu setup, there is no clear runtime disclosure or confirmation that content will be transmitted to third-party services.

External Transmission

Medium
Category
Data Exfiltration
Content
if [ -n "$FEISHU_WEBHOOK" ]; then
    NEWS_CONTENT=$(head -c 3000 "$OUTPUT")
    MESSAGE=$(jq -n --arg content "$NEWS_CONTENT" '{"msg_type":"text","content":{"text":$content}}')
    curl -X POST -H "Content-Type: application/json" -d "$MESSAGE" "$FEISHU_WEBHOOK" > /dev/null 2>&1
    echo "✅ 已推送到飞书"
fi
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.