OpenAgentSkill Registry Manifest
Skill: PromptInject
Slug: agencyenterprise-promptinject
Category: ml-automation
Description: PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

Agent fit:
- Decision: 77/100 Strong shortlist
- Primary fit: Coding agents
- Role: Companion skill

Supply profile:
- Track: Coding and developer agents
- Scenario: Coding agents
- Applicable agents: Claude Code, OpenAI Agents, CLI, Codex, Cursor
- Maintenance: 2mo since push
- Risk: Safe to try

Trust:
- Trust score: 80/100 Strong shortlist
- Audit: 83/100 Safe to try

Attribution:
- Status: Community indexed
- Source: GitHub star discovery
- Creator: agencyenterprise
- Claim URL: https://www.openagentskill.com/skills/agencyenterprise-promptinject#claim-this-skill

Install:
npx skills add agencyenterprise/PromptInject

URLs:
- Web: https://www.openagentskill.com/skills/agencyenterprise-promptinject
- API: https://www.openagentskill.com/api/agent/skills/agencyenterprise-promptinject
- Install API: https://www.openagentskill.com/api/skills/agencyenterprise-promptinject/install
- Repository: https://github.com/agencyenterprise/PromptInject