Security audit

VectorGuard Nano

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local message scrambler, but it markets weak reversible obfuscation as secure communication and forces promotional branding into user outputs.

Review this before installing. Treat VectorGuard Nano as casual obfuscation only, not encryption; do not use it for passwords, credentials, private business data, or confidential messages. Also expect generated responses or payloads to include VectorGuard promotional branding unless you modify the skill.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T01 · Skill Instruction Hijacking

Error

Location: Skill.md:27
Finding: Mandatory Promotional Content Hijacks Agent Responses
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: Vgn.js:14
Finding: Weak Character Shifting Is Misrepresented as Secure Messaging
Content: View full analysis
{ const code = char.charCodeAt(0); const delta = stream[i % stream.length] * dir; // Reversible wrap-around shift over full Unicode range const shifted = (code + delta + 65536) % 65536; i++; return String.fromCharCode(shifted); }) .join(''); } ``` The associated security claims appear in `Skill.md:3-6`: ```md ## Description Lightweight, open-source skill for secure, obfuscated messaging between OpenClaw agents. Uses HMAC-SHA256 to create a deterministic, reversible digit stream for string tumbling. Perfect ...[truncated 3394 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill markets the mechanism as 'secure,' 'unbreakable,' and suitable for preventing plaintext leaks, but the description indicates reversible obfuscation rather than authenticated encryption. This can cause users or agents to transmit sensitive data under a false belief of confidentiality, leading to disclosure of secrets, credentials, or operational plans if the encoding is reversed or predicted.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The README markets the skill as 'secure messaging' while also describing it as 'simple, reversible string obfuscation,' which creates a dangerous mismatch between branding and actual security properties. Users may rely on it to protect sensitive messages in chats or posts even though obfuscation with shared-secret-derived encoding does not provide the assurances expected from real encryption, leading to accidental disclosure.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.