ClawHub
Back to skill

Security audit

Social Content Topic Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward third-party content-planning API skill, with the main caution that user marketing details are sent to wsdsocial.com.

Install this only if you are comfortable sending account positioning, niche strategy, and audience descriptions to wsdsocial.com. Avoid entering confidential campaign plans, customer data, or regulated information, and keep WSD_API_KEY scoped and private.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad and include very common terms such as "topic," "headline," "content planning," and "trending," which can cause the skill to activate on generic user requests that do not clearly imply consent to use this external service. Over-broad activation increases the chance of accidental invocation and unintended transmission of user-provided business ideas or audience data to the third-party API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation shows that account direction and target audience are sent to ai.wsdsocial.com, but it does not warn users that their inputs are transmitted to a third-party service. This can undermine informed consent and may expose sensitive marketing strategy, audience segmentation, or business planning data to an external processor without the user's awareness.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill explicitly transmits user-supplied content to an external endpoint using an API key header, creating a real data egress path to a third-party service. In this skill's context, the data appears to be marketing-related rather than highly privileged system data, which lowers severity somewhat, but the risk remains significant if users include confidential campaign plans, niche strategy, or customer targeting details.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

Usage

bash
curl -X POST "https://ai.wsdsocial.com/api/pub/skills/red-note-content-topic/_tool_88" \
-H "Content-Type: application/json" \
-H "key: ${WSD_API_KEY}" \
-d '{

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language trigger description includes both English and Chinese terms such as '选题 / 选题策划 / 爆款标题' without stating whether the skill operates bilingually by user choice. This can create a locale-policy issue because the skill appears to assume mixed-language activation rather than explicitly offering language selection or clarifying the intended audience.

Content

No source excerpt is available for this finding.