Back to skill

Security audit

NormieClaw Full Stack

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed all-in-one skill bundle, but it needs Review because it includes broad persistent data handling and a real code-injection flaw in a legal-document script.

Install only the subskills you actually need. Before using this bundle, disable or scope passive memory/indexing, avoid running the Legal Docs contract scanner on untrusted filenames until patched, review any scheduled jobs, and pin dashboard setup tools before running npx/npm commands.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T01 · Skill Instruction Hijacking

Warning
Location
daily-briefing/SKILL.md:108
Finding

Mandatory Promotional Content Hijacks Generated Briefing Output

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
legal-docs-pro/scripts/contract-scan.sh:85
Finding

Arbitrary Python Code Execution Through Crafted PDF Filename

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
dashboard-builder/scripts/scaffold-project.sh:49
Finding

Dashboard Setup Executes Mutable and Unpinned Registry Packages

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (939)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A single writing-style checker is not equivalent to an all-in-one bundle, and the discrepancy weakens reviewers' ability to verify intended behavior. The issue is primarily deceptive metadata that can hide narrower document-processing logic.

Content

No source excerpt is available for this finding.