Caveat verdict

macos-terminal-beautify

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Fetches from network AND uses eval/Function

Terminal beautification skill installing Ghostty, Starship, Oh My Zsh, and Nerd Fonts via Homebrew; the curl|sh install of Oh My Zsh is from the well-known official source, and all other steps are standard package manager installs.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
60
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)

LLM05 · LLM06 · ASI05

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf ~

Pattern match high

Accesses shell history/config

SKILL.md · code · ~/.zshrc

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/C/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installnetwork_outdynamic_eval
Check another skill Browse the registry Auditing your own skills or configs? Use the API