Promptinjection
Test agent prompts and tool boundaries for injection risks before production use, documenting unsafe instruction paths and hardening system prompts against untrusted user or document content.
npx skills add https://github.com/danielmiessler/personal_ai_infrastructure --skill promptinjection| Installs | 120 |
|---|---|
| Repository | danielmiessler/personal_ai_infrastructure ↗ |
Related skills
Azure ComplianceRun Azure best-practice and compliance scans with azqr and audit Key Vault keys, secrets, and certificates before or after shipping workloads.396k1.2k
Openclaw Secure Linux CloudDeploy OpenClaw on a hardened Linux cloud VPS with rootless Podman and SSH-tunneled control UI access.221k61Entra Agent IdProvision Microsoft Entra Agent Identity blueprints and per-instance agent principals, then configure OAuth fmi_path and OBO token exchange for production AI agents.121k1.2k
Firebase Security Rules AuditorRed-team Firestore security rules after edits so solo builders catch update bypasses and authority bugs before production.48.9k345Firestore Security Rules AuditorRed-team Firestore security rules after edits so create/update gaps, authority spoofing, and abuse paths get caught before production.20.3k345
Skill VetterRun a conservative, manual-first security checklist on OpenClaw SKILL.md packages before installing from ClawHub, GitHub, or shared files.19.6k62