ClawHub
Back to skill

Security audit

Red Note Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple documented wrapper for sending RED note text to a third-party audit API, with no hidden code or persistence.

Install only if you are comfortable sending the full RED note text to ai.wsdsocial.com for processing. Do not submit confidential, regulated, or client content unless you have authority to share it, and keep the WSD_API_KEY out of source control, logs, and screenshots.

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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The skill explicitly performs external transmission by POSTing user-provided content and an API key to ai.wsdsocial.com. In context this appears to be the intended SaaS architecture rather than covert exfiltration, but it is still a real security-relevant behavior because user content is sent off-platform to a third party and therefore requires clear disclosure and trust assumptions.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

Usage

bash
curl -X POST "https://ai.wsdsocial.com/api/pub/skills/red-note-audit/_tool_87" \
  -H "Content-Type: application/json" \
  -H "key: ${WSD_API_KEY}" \
  -d '{

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to send full RED note content to a third-party API but does not clearly warn that the content leaves the local environment and is processed by wsdsocial.com. This creates a privacy and data-handling risk, especially if users submit unpublished, sensitive, client, or regulated content assuming the audit happens locally or within a trusted first-party boundary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The setup section tells users to place an API key in an environment variable but provides no guidance on secure credential handling, scope, or avoidance of accidental exposure. While using environment variables is common practice, the absence of any warning can contribute to mishandling in shared shells, logs, screenshots, CI systems, or misconfigured environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.