Audits a Claude Code skill for security risks in three modes: before download (from a URL or install command), after download but before install (from a .skill file), or after install (from a local skills directory). Use this skill whenever a user is about to install a skill from any source — including GitHub URLs, git clone commands, npx/npm commands, curl/wget downloads, pip installs, marketplace links, or raw SKILL.md URLs. Also trigger when a user asks "is this skill safe?", "should I trust this skill?", "can you check this before I install it?", "audit this skill", or pastes any link to a skill repository or .skill file. If a user mentions installing ANY skill, proactively offer to audit it first — do not wait for them to ask.
97
97%
Does it follow best practices?
Impact
99%
1.28xAverage score across 5 eval scenarios
Advisory
Suggest reviewing before use
Contains a sample report produced by skill-safety-auditor to demonstrate
the format and range of findings the tool can surface.
The report in sample-report.md was produced by auditing the purpose-built
test skill at test-fixtures/test-skill-with-known-issues/.
Previous version: The original sample was produced against a live public
third-party skill (hundred-million-offers from wondelai/skills). That report
only produced warnings (no critical findings) and referenced an external source
that readers could not easily verify themselves.
Current version: The sample now audits a test fixture that lives in this repository. This means:
See test-fixtures/README.md for a full description of the fixture and how to
use it to verify the auditor's output on your own machine.
audit-sample
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5