No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by mturac · Codex Skill · ★ 81
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is promptguard safe to install? View the security audit →
Prompt contracts for agent workflows. Offline · deterministic · zero dependencies Agents do what you ask — even when what you ask is incomplete. PromptGuard treats that line as a contract, not a wish. It checks whether role, surface, constraints, verification, and safety are explicit enough to execute — and stops vague instructions before they become a bad write. Install What you get No model calls. No network. Safe in hooks and air-gapped machines. Profiles bash prom
| Stars | 81 |
| Forks | 0 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 53.3618072424764/100 |
| Last Updated | 2026-07-22 |
| Created | 2026-04-26 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~13k |
These tools work well together with promptguard for enhanced workflows:
Looking for a promptguard alternative? If you're comparing promptguard with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CL
Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions,
Explore other popular codex skill tools:
promptguard is Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.. It is categorized as a Codex Skill with 81 GitHub stars.
promptguard is primarily written in Python. It covers topics such as agent-skills, ai-agents, claude-code.
You can find installation instructions and usage details in the promptguard GitHub repository at github.com/mturac/promptguard. The project has 81 stars and 0 forks, indicating an active community.
promptguard is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to promptguard on Agent Skills Hub include agent-skills, maestro, open-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: