ClawHub
Back to skill

Security audit

Nishare Api

Security checks for vulnerabilities and agentic risk

Overview

This skill documents how to publish or update user-provided content on Nishare, with clear external API use and no hidden local code, but users should avoid sending sensitive content or exposing API keys.

Install only if you intend agents to publish or update content on Nishare. Review content before upload, do not include secrets or private data in shared pages/documents/images, and provide API keys only when authenticated publishing or updates are actually needed.

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 (7)

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill is fundamentally designed to transmit AI-generated HTML, images, documents, and optionally authentication credentials to an external service, which creates a real external-transmission risk. In this context the behavior is expected functionality, but it is still security-relevant because agents may send sensitive content or organization-scoped credentials to Nishare without sufficient disclosure or consent safeguards.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: nishare-api
description: Use when the user wants to publish, update, or explain how to publish AI-generated HTML, image, or document content to Nishare via its API, needs curl examples, API-Key/Bearer authentication, 工作组 targeting, payload validation rules, or wants an agent prompt that returns a Nishare shareUrl.
metadata:
  short-description: Publish and update Nishare shares
---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs use of API-Key/Bearer authentication for publishing into an account or updating content, but it does not warn that prompts, generated content, and credentials will be sent to a third-party external service. In agent contexts, this omission can lead to unintended exfiltration of sensitive data or tokens because users may not realize the action crosses a trust boundary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file documents /api/ai/publish as allowing anonymous publishing and /api/ai/update as modifying an existing project, but it does not include a user-facing warning that these actions send user content to a remote service and may create or alter shared content. For markdown files, missing warnings about behaviors that affect user data, privacy, or system integrity should be flagged.

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 · references/api.md (reported line 76)May include surrounding context.

Publish HTML JSON

bash
curl -s https://nishare.com/api/ai/publish \
  -H 'Content-Type: application/json' \
  -d '{"title":"AI 生成演示","type":"html","html":"<!doctype html><html><body><h1>Hello</h1></body></html>"}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The copyable agent prompts are written only in Chinese and instruct downstream AI tools in that language, while the surrounding skill documentation is otherwise in English. This creates a language/locale constraint without user opt-in or justification, which matches the natural-language policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file includes Chinese-only terms such as 工作组 in field descriptions and Chinese response messages in examples, implying locale-specific output or terminology without documenting user choice or a region-specific requirement. This is a natural-language policy concern because the documentation presents a specific language/locale without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Multiple examples use Chinese titles, markdown content, and response messages such as 已更新 Nishare 项目 and 内容审核未通过，命中敏感词：example, but the reference does not state that language is configurable or region-specific. This may violate language/locale policy by effectively forcing one locale in examples and documented outputs.

Content

No source excerpt is available for this finding.