Back to skill

Security audit

Viral Note Imitation Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple, disclosed API wrapper for generating social marketing drafts, with privacy cautions because it sends user-provided content to wsdsocial.com.

Install only if you are comfortable sending the reference post, product details, and selling points to wsdsocial.com. Avoid submitting confidential business plans, private customer data, credentials, or copyrighted text you are not allowed to share, and invoke the skill intentionally for social-note imitation tasks.

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
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
93% confidence
Finding

The trigger keywords are broad enough to match ordinary writing and rewrite requests, which can cause the skill to activate unexpectedly in situations where users did not intend to send content to this external service. In this skill, that risk is amplified because activation may lead to transmission of reference posts, product details, and marketing strategy data to a third-party API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill documents sending the user's reference content, product information, and selling points to an external API but does not clearly warn users about that data transfer. This creates a meaningful privacy and confidentiality risk because users may provide copyrighted source text, internal marketing plans, or sensitive business information without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The skill explicitly sends user-supplied content to an external endpoint, which is a real data egress surface. In context, this is expected functionality rather than hidden exfiltration, but it still becomes dangerous if users provide sensitive reference text, credentials, proprietary product plans, or personal data without clear notice and consent.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

Usage

bash
curl -X POST "https://ai.wsdsocial.com/api/pub/skills/red-note-imitation-writing/_tool_89" \
-H "Content-Type: application/json" \
-H "key: ${WSD_API_KEY}" \
-d '{

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The invocation guidance includes Chinese-only trigger examples ("爆款仿写" and "对标爆款") alongside English text, but the file does not explain whether the skill is restricted to Chinese-language usage or offer users a language/locale option. This can create an implicit locale preference without explicit opt-in or justification.

Content

No source excerpt is available for this finding.