Website Audit

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

Overview

The skill is a simple website-audit instruction set with no bundled code, but it relies on an undeclared external `squirrel` command and includes an optional example that pipes audit results to another AI tool.

This appears safe as an instruction-only website-audit helper. Before installing, confirm you trust the `squirrel` CLI that will actually run, audit only websites you are authorized to test, and be careful before piping reports to external AI services.

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

The command may fail or may run whatever `squirrel` executable is already on the user's PATH, so provenance matters.

Why it was flagged

The skill's main workflow depends on an external `squirrel` CLI, while the supplied install/requirements metadata declares no required binaries and provides no install source.

Skill content
squirrel audit https://example.com
Recommendation

Verify the source, path, and version of the `squirrel` CLI before using this skill.

What this means

Audit results may include URLs, page metadata, issues, and recommendations that could be shared with an external AI service if the user follows this example.

Why it was flagged

The reference documentation includes a user-directed example that sends audit output to another AI agent.

Skill content
squirrel audit https://example.com --format llm | claude
Recommendation

Review audit output before piping it to another AI tool, and avoid sending sensitive or private site data to untrusted providers.