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
A developer on your team installed a Claude Code skill last week from a trusted colleague's GitHub repo. Now your security team has asked everyone to verify that all installed skills are safe, as part of a new audit policy. You need to audit the skill and produce documentation confirming it was reviewed.
The skill was installed and its files are provided below. Treat these as files from the installed skills directory on the local system.
Extract these files before beginning:
Reads recent git commit messages and produces a formatted changelog section.
Ask me to summarize commits since a given date or tag. I'll run git log to fetch the messages and format them into a readable changelog entry.
git log with appropriate flags to fetch commit messagesProduce a file called compliance-audit.md containing:
The compliance team will use this document as evidence that the skill was reviewed. Make it thorough enough to stand on its own.
audit-sample
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5