Back to skill

Security audit

Randomization Gen

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to do its advertised RCT randomization task, but it needs Review because it can overwrite arbitrary writable files and makes an unsupported clinical allocation-concealment claim.

Review carefully before installing. Run it only in a sandbox or controlled workspace, pass an output path that is inside the project, and avoid overwriting existing files. Do not rely on this draft script for regulated or high-stakes clinical allocation concealment without a validated randomization process and appropriate access controls.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/main.py:56
Finding

Unrestricted Output Path Allows Arbitrary File Overwrite

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/main.py:19
Finding

Non-Cryptographic Random Generator Used for Concealed Clinical Allocation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises file-writing behavior but does not declare an explicit tool scope such as permissions or allowed-tools. This creates an authorization ambiguity where an agent or reviewer cannot easily determine whether filesystem modification is intended, increasing the risk of unintended or overly broad writes if the skill is executed in a permissive environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill mentions creating output files but does not clearly warn users that running it will modify the filesystem or specify where files will be written. This can lead to unexpected file creation, overwrites, or confusion about artifact locations, especially in shared or automated workspaces.

Content

No source excerpt is available for this finding.