Skip to main content
Scans/clawhub/skill-safety-checker

skill-safety-checker

clawhub

Share

Summary

skill-safety-checker v1.0.0 was classified as LOW RISK with a risk score of 4. Sigil detected 2 findings across 4 files, covering phases including install hooks. Review the findings below before installing this package.

LOW RISK(4)

v1.0.0

8 June 2026, 05:31 UTC

by Sigil Bot

Risk Score

4

Findings

2

Files Scanned

4

Provenance

Findings by Phase

Phase Ordering

Phases are ordered by criticality, with the most dangerous at the top. Click any phase header to expand or collapse its findings. Critical phases are expanded by default.

install-makefile-curl

LOW

Makefile/script pipes remote content to shell

SKILL.md:53


- **Unsafe execution patterns:** Does the skill tell the agent to run code that comes from the network, user input, or another skill without validation? (e.g. `curl … | sh`, `wget … -O - | bash`, `eval "$(…)"`, running a script URL directly.)
- **Piped installs:** Any instruction to pipe remote content into shell/interpreter (curl/wget to bash/python/node) is high risk — treat as suspicious unless the URL is a well-known, integrity-checked official source.
Why was this flagged?

A script or Makefile pipes content from a remote URL directly into a shell (curl | sh or wget | bash). This is inherently dangerous because the remote content can change at any time, and the command runs with the current user's permissions. Rated HIGH because it requires manual execution (unlike install hooks) but still executes arbitrary remote code.

install-makefile-curl

LOW

Makefile/script pipes remote content to shell

reference.md:36

| **Instruction scope** | Instructions should only reference files, endpoints, and actions that fit the stated purpose. Do not tell the agent to read unrelated system files or send data to undeclared endpoints. |
| **Remote code execution (RCE)** | Do **not** instruct the agent to: run `curl … \| sh` or `wget … \| bash`; use `eval` on remote or user-supplied input; build shell commands from unvalidated strings; or run remote/dynamic code as root or with sudo. Use fixed, local scripts or well-kno
Why was this flagged?

A script or Makefile pipes content from a remote URL directly into a shell (curl | sh or wget | bash). This is inherently dangerous because the remote content can change at any time, and the command runs with the current user's permissions. Rated HIGH because it requires manual execution (unlike install hooks) but still executes arbitrary remote code.

Badge

Sigil scan badge for clawhub/skill-safety-checker

Markdown

[![Sigil Scan](https://sigilsec.ai/badge/clawhub/skill-safety-checker)](https://sigilsec.ai/scans/CAA148EC-19CA-4E62-B80F-A96F4109978A)

HTML

<a href="https://sigilsec.ai/scans/CAA148EC-19CA-4E62-B80F-A96F4109978A"><img src="https://sigilsec.ai/badge/clawhub/skill-safety-checker" alt="Sigil Scan"></a>

Run This Scan Yourself

Scan your own packages

Run Sigil locally to audit any package before it touches your codebase.

curl -sSL https://sigilsec.ai/install.sh | sh
Read the docs →Free. Apache 2.0.

Sigil Pro

Cloud scanning, AI investigation, web dashboard, and CI/CD integration. 30-day free trial.

Start free trial →

Get threat intelligence and product updates

Security research, new threat signatures, and product updates. No spam.

Other clawhub scans

Believe this result is incorrect? Request a review or see our Terms of Service and Methodology.

Scanned bySigil Bot