Observed arrival · 2026-10-24
Stingward checks the work AI helped you ship
An open-source security checker audits AI-built apps, agent skills, and MCP servers, then grades findings and suggests fixes.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- AI-assisted app and agent-skill builders
- Worth noticing
- A sample skill audit flags invisible Unicode instructions alongside credential access and outbound network calls in setup.sh.
Field notes
Examples on the page show the CLI auditing a skill folder and a Next.js project, then printing findings with file locations, severity, rule identifiers, explanations, and fixes; the page also offers HTML and PDF report formats. Installation routes listed include pipx, npx, Claude Code/Codex plugins, and a GitHub Action. The site says its 55 rules map to CWE and OWASP and its 1,045 tests run on Linux, macOS, and Windows.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue