ClawHub

1password Temp

Security checks across malware telemetry and agentic risk

Overview

This 1Password CLI skill is coherent, but its examples can expose or persist secrets, so users should review it carefully before installing.

Review before installing. Use this skill only when you are comfortable allowing the agent to operate `op` against your 1Password account, and specify the exact account, vault, item, and field it may access. Avoid `--no-masking` and avoid writing secrets to files unless you explicitly need that behavior, set restrictive permissions, keep outputs out of source control, and delete them promptly.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The examples include commands that write secret material to local files and inject secrets into configuration output without any warning about secure file permissions, cleanup, or avoiding persistence. In documentation for a secrets-management CLI, this can lead users to store sensitive values on disk in ways that are later exposed through backups, logs, world-readable files, or source control.

Missing User Warnings

High
Confidence
98% confidence
Finding
The example explicitly disables masking with `--no-masking` and then prints `DB_PASSWORD`, causing the secret value to be exposed directly to the terminal and potentially to shell history capture, CI logs, screen recording, or monitoring systems. Because this is presented as a normal usage example, users may copy it into real environments and unintentionally leak credentials.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal