Observed arrival · 2026-09-11
SkillLock scans AI-agent Skills before they run
A static security scanner for Codex, Claude Code, and Cursor Skills that flags risky permissions, data transfers, secret access, and hidden instructions.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
Local scans are performed in the browser, and the page says the selected files are not uploaded; GitHub-link scans instead fetch supported text files from the referenced repository. The stated limit is up to 100 text files, with folder and file links constrained to the selected location. Findings are organized around observable behavior, review-needed context, and lower-risk information rather than a blanket safety verdict.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue