Password Generator

Security checks across malware telemetry and agentic risk

Overview

This skill generates passwords but automatically stores them in a plaintext markdown file, so users should review the secret-retention risk before installing.

Install only if you are comfortable with every generated password being printed and saved in plaintext under the OpenClaw workspace memory directory. For real account credentials, prefer a trusted password manager or modify the skill to use cryptographic randomness and avoid saving passwords unless the user explicitly asks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill performs file-write behavior by instructing the agent to save generated passwords to `memory/passwords.md`, but no corresponding permission or disclosure is declared. This is dangerous because it introduces silent persistent storage of sensitive secrets, expanding the attack surface and violating least-privilege expectations for a password-generation tool.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The stated purpose is password generation, but the skill also persists the generated password, date, and metadata to local storage in plaintext. That mismatch is security-relevant because users may reasonably expect ephemeral password generation, while the actual behavior creates a durable secret repository that can be read later by other tools, users, or compromised processes.

Description-Behavior Mismatch

High
Confidence
99% confidence
Finding
The skill’s stated purpose is to generate secure passwords, but it also silently persists each generated password to a local file. Storing newly generated secrets in plaintext expands exposure well beyond the immediate session and creates a sensitive artifact that can be read later by other processes, users, backups, or logs.

Context-Inappropriate Capability

High
Confidence
99% confidence
Finding
The code writes plaintext passwords into a persistent memory file without any security control, despite the skill only needing to generate a password. Plaintext secret storage is dangerous because compromise of the host, workspace, backups, or shared environment immediately exposes all saved passwords.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill does not warn users that generated passwords will be written to persistent storage, despite handling highly sensitive credentials. This is dangerous because users may expose secrets unknowingly, and plaintext storage of passwords creates a high-value target for later disclosure or unauthorized reuse.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill saves generated passwords without informing the user or obtaining confirmation, violating user expectations for a password generator. This makes accidental secret retention likely and increases the chance that users believe a password was ephemeral when it was actually stored persistently.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal