Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.
How to install tool-abuse-detection?
tencent/ai-infra-guard/tool-abuse-detection
$npx -y skills add tencent/ai-infra-guard --skill tool-abuse-detectionInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/tencent/ai-infra-guard" --skill "tencent/ai-infra-guard/tool-abuse-detection"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/tencent/ai-infra-guard" that are relevant to the current task. Run `npx skills add "https://github.com/tencent/ai-infra-guard"` and select the relevant skills, then follow their instructions.
Related
6 picksType
- entra-app-registrationGuides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration.Jul 2026
- azure-complianceRun Azure compliance and security audits with azqr plus Key Vault expiration checks.Jul 2026
- entra-agent-idProvision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token…Jul 2026
- firebase-security-rules-auditorAudits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource…Jul 2026
- golang-securitySecurity best practices and vulnerability prevention for Golang.Jul 2026
- gws-modelarmorGoogle Model Armor: Filter user-generated content for safety.Jul 2026
