by mturac · Codex Skill · ★ 59
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pipx install "git+https://github.com/mturac/promptguard.git"
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 | 59 |
| Forks | 1 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 53/100 |
| Last Updated | 2026-07-22 |
| Created | 2026-04-26 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~13k |
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.
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
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,
elastic inference for your agentic workloads
Explore other popular codex skill 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: