Maps AI-generated code gaps to OWASP LLM Top 10 with exact references and remediation list.
npx skills add https://github.com/fnkydcks-lab/dt-foundry --skill llmcodecheck
Please help me install this Agent Skill. Skill: /llmcodecheck Source: https://github.com/fnkydcks-lab/dt-foundry/tree/main/llmcodecheck Command: npx skills add https://github.com/fnkydcks-lab/dt-foundry --skill llmcodecheck
AI-generated code gaps are common and can introduce security and reliability risks. This skill provides a structured OWASP LLM Top 10-based audit to identify what the model left open, what it assumed, and what it didn't handle.
Run the /llmcodecheck command to generate an OWASP-aligned gap report for the current codebase.
High-intent search queries and answers about installing and using this skill.
You can audit AI-generated code for OWASP LLM Top 10 vulnerabilities by running a command that scans lib/, supabase/functions/, and supabase/migrations, mapping each finding to a category with exact line references and remediation suggestions.
AI-generated code gaps typically include unhandled edge cases, incorrect security assumptions, and missing validation logic. An OWASP LLM Top 10 audit identifies what the model left open, assumed, or failed to handle before shipping.
To generate an OWASP code audit report for a Supabase codebase, scan the lib/ and supabase/ directories. The process outputs a Markdown report at .dt-foundry/llmcodecheck.md containing categorized findings and actionable fixes.
Yes, automated security scans work for mobile and web stack code by applying OWASP-aligned gap detection across the full codebase. This produces a concrete findings report with category, exact line references, and remediation suggestions.
The best way to remediate AI code vulnerabilities before shipping is to generate a prioritized, actionable remediation list. This ensures each finding includes the OWASP category, exact line, plain-language risk, and a recommended fix.
No, the OWASP LLM Top 10 audit requires no external dependencies. It directly analyzes the codebase in lib/, supabase/functions/, and supabase/migrations to produce a standalone Markdown findings report.
AIBiz-AutomatyzacjeAudits React 19 + Supabase + Edge Functions projects for security vulnerabilities.
fnkydcks-labCoordinate design and engineering review via six framework lens passes.
PriyanshKuniyalConfigures and manages SAST tools for automated vulnerability detection in CI/CD pipelines.
DevHive1Orchestrate dependency, static analysis, and privacy dataflow scanners into prioritized reports.
