my_skill

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent 1Password CLI helper with no bundled code, but it necessarily lets an authorized agent handle vault secrets, so use it only for specific, intentional secret tasks.

This skill appears safe for its stated purpose if you want an agent to help with 1Password CLI setup and use. Before installing, be comfortable with the agent operating an authorized 1Password CLI session, keep requests specific to the exact vault/item needed, avoid unmasked secret output, and make sure the tmux session is closed after use.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If you unlock and authorize 1Password, the agent may be able to run op commands for the selected account and access secrets you direct it to use.

Why it was flagged

The skill is explicitly designed to use an authorized 1Password account and vault secrets. This is purpose-aligned, but it gives the agent access to high-value credentials once the user authorizes the CLI.

Skill content
description: Set up and use 1Password CLI (op)... reading/injecting/running secrets via op.
Recommendation

Authorize only the intended 1Password account, specify exact vault/item references, and avoid broad or exploratory secret-reading requests.

What this means

Secrets could end up in terminal output, tmux pane history, chat transcripts, or local files if these examples are used carelessly.

Why it was flagged

These examples can write secrets to local files or print unmasked secrets to the terminal. The main skill guardrails warn against putting secrets in logs or chat, so this is a sensitive-use note rather than evidence of hidden behavior.

Skill content
`op read --out-file ./key.pem op://app-prod/server/ssh/key.pem`; `op run --no-masking -- printenv DB_PASSWORD`
Recommendation

Prefer `op run` or `op inject` without printing secret values, avoid `--no-masking` unless absolutely necessary, and delete any temporary secret files promptly.

What this means

If a tmux session is left running, command history or command output could remain accessible locally longer than intended.

Why it was flagged

The skill uses a detached tmux session to preserve an interactive 1Password CLI authentication flow. This is disclosed and purpose-aligned, but it is temporary background state that may retain output until closed.

Skill content
REQUIRED: create a fresh tmux session for all `op` commands... `tmux -S "$SOCKET" new -d -s "$SESSION"` ... `tmux -S "$SOCKET" kill-session -t "$SESSION"`
Recommendation

Confirm the tmux session is killed after use and avoid running commands that display raw secrets in that session.

What this means

Installing the skill may require installing the 1Password CLI from Homebrew, so trust in the package source matters.

Why it was flagged

The skill installs an external CLI package through Homebrew. This is expected for a 1Password CLI helper and there is no bundled code, but it still relies on the package manager and upstream package source.

Skill content
"install": [{ "id": "brew", "kind": "brew", "formula": "1password-cli", "bins": ["op"] }]
Recommendation

Install only from the official 1Password/Homebrew source and compare with the linked official 1Password CLI documentation if unsure.