Back to skill

Security audit

Multi Platform Publish

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a social-content generation guide, but it hard-codes a branded hashtag into user-facing output, so it should be reviewed before installation.

Install only if you are comfortable reviewing or overriding generated tags before publishing. The main operational risk is not system compromise; it is that generated Xiaohongshu content may include the fixed #虾闯天下 tag unless the user or agent removes it. Also confirm any localhost rendering service is one you intentionally run.

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
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:18
Finding

Mandatory Branded Hashtag Injection into Generated Content

Content
View full analysis
Remediation
View remediation
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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is entirely specified in Chinese and includes prescriptive style requirements such as using '兄弟们', emoji, and other Chinese-platform-native phrasing for generated copy. This effectively forces a specific language/locale and tone without stating that the user can choose another language or opt in to Chinese output.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 41)May include surrounding context.

固定接口(不推荐用于多平台)

bash
curl -X POST "http://localhost:3710/api/content/render" \
  -d '{"cover_word":"标签","cover_title":"标题","cover_description":"描述","cover_emoji":"🤖"}'

⚠️ 尺寸固定,不能自定义宽高比例