inkog-io

Inkog — Security skill for Claude Code

Security community

Static security scanner for AI agents.

How to install Inkog

This entry records only its repository, not the path inside it, so there is no exact command to give. Open inkog-io/inkog and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Inkog does

Static security scanner for AI agents. Catches prompt injection, runaway loops, missing oversight, and compliance gaps across 21 frameworks. Use from Claude Code, Cursor, ChatGPT (MCP), the CLI, or GitHub Actions.

Alternatives in Security

  • Promptmap — Security scanner for custom LLM apps 1.2k ★
  • Code Audit — Adversarial code review tree 123 ★
  • Sail Skill — SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, secur 122 ★

README

Inkog

The pre-flight check for AI agents.

Static analysis that catches the bugs only agent code can have — token bombing, prompt injection, missing oversight, compliance gaps — before they ship.

Release License Go Report Card CI Discord

Inkog scanning AI agent code for vulnerabilities

Inkog dashboard report — findings, code-level analysis, EU AI Act / NIST / OWASP compliance mapping
Every scan is a shareable report — view this one live

Why Inkog

Most security tools find SQL injection. Inkog finds the things that **only break in agent code**:

  • Token bombing — loops where the LLM controls termination, draining your API budget
  • Recursive tool calling — one user request fans out into 10,000 LLM invocations
  • Prompt injection sinks — RAG output flowing into a system prompt

Related Skills

Code Validator — Security skill for Claude Code

Code Validator

Static security scanner purpose-built for AI-generated code (Claude Code, GitHub Copilot, ChatGPT, Cursor). De

Security community
Vibe Audit — Security skill for Claude Code

Vibe Audit

Security scanner for AI-built apps. Catches hardcoded secrets, injection vulnerabilities, missing rate limits,

Security community
Vibe Secure — Security skill for Claude Code

Vibe Secure

Security audit for AI-generated code. Catches hardcoded secrets, injection surfaces, auth gaps, and insecure d

Security community
Skill Lint — Security skill for Claude Code

Skill Lint

Security scanner for Claude Code / agent skills. Catches prompt injection, obfuscation, credential exfiltratio

Security community
Headless Harness Bench — Security skill for Claude Code

Headless Harness Bench

Benchmark of 6 coding-agent harnesses (omp/pi/fx/opencode/dsh/crush) as headless agent loops driven by a contr

Security community
Prowler Studio — Security skill for Claude Code

Prowler Studio

Prowler Studio an AI workflow that ensures Claude Code follows Prowler's guardrails to deliver consistent, tes

Security community

Related Agents

Seraph — Security agent for Claude Code

Seraph

Static security audit of a repo's code and config (exposed secrets, missing authorisation, injection surfaces,

Security community
Host Reviewer — Security agent for Claude Code

Host Reviewer

Use this agent to audit an mcp-use server against one host's checklist (ChatGPT or Archestra Route A) and retu

Security community
AI Agent Engineer — Data & AI agent for Claude Code

AI Agent Engineer

Specialist in designing, building, and deploying autonomous AI agents and multi-agent systems. Delegate when y

Data & AI community