by boxed-dev · LLM Plugin · ★ 216
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/boxed-dev/cognidb
Taken from the project's README on GitHub.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 216 |
| Forks | 18 |
| Language | Python |
| Category | LLM Plugin |
| License | MIT |
| Quality Score | 73/100 |
| Last Updated | 2026-08-01 |
| Created | 2024-12-06 |
| Platforms | aws, python |
| Est. Tokens | ~14k |
CogniDB 3.0 Secure natural-language SQL for applications — a Python library, not a chat product. CogniDB turns natural language into SELECT-oriented SQL against PostgreSQL, MySQL, and SQLite. Security is the product: sanitize → generate → validate → allowlists → execute → audit. Status: Git / source release 3.0.1 is ready to install from this repo (GitHub Release).
These tools work well together with cognidb for enhanced workflows:
Looking for a cognidb alternative? If you're comparing cognidb with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read.
Established strong JEV based natural language to SQL performance and well-covered semantic operators for Postg
Give AI assistants full PostgreSQL DBA superpowers — 30+ tools for performance analysis, bloat detection, lock
SQL static analyzer for performance, security, compliance and cost. 272 rules. Completely offline. Works in C
Open-source text-to-SQL engine you tune and measure on your own database
Agent samples built using the Strands Agents SDK.
Explore other popular llm plugin tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: