agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.

Source

Creator's repository · affaan-m/everything-claude-code

View on GitHub

Security

Security checks in progress
Results will appear here once audits complete
What this skill can do
Reads your filesConnects to the internetRuns code on your machine
Checked by 3 independent security firms
Does it try to trick the AI?Not yet checkedPending · Gen Agent Trust Hub
Does it sneak in hidden code?Not yet checkedPending · Socket
Does it have known bugs?Not yet checkedPending · Snyk