llm-app-securitylisted

# LLM App Security The prompt and the tools are one layer of the story. This skill covers the other layer: **the operational side** of running an LLM-powered feature in production. The threats are mostly mundane (abuse, cost, leak, compliance), the controls mostly familiar from API security, applied to a substrate that has new failure modes. Companion to [`prompt-injection-defense`](../prompt-injection-defense/SKILL.md) (prompt layer) and [`ai-agent-guardrails`](../ai-agent-guardrails/SKILL.md) (tool layer). ## When to invoke - Designing or reviewing an LLM feature before public launch - Investigating unusual API spend or 429s - Handling an abuse complaint ("your AI told a user to ...", "your AI leaked ...") - After a model-provider security advisory - Periodic re-review of an existing LLM product surface ## The OWASP LLM Top 10 — practical mapping Walk these against your app. Most issues fall under one of these. | ID | Issue | Practical control | |---|---|---| | LLM01 | Prompt injection | See [`prompt-injection-defense`](../prompt-injection-defense/SKILL.md) | | LLM02 | Insecure output handling | Treat model output as untrusted: escape, sanitize, validate before acting | | LLM03 | Training-data poisoning | Mostly upstream; pick reputable providers, version-pin | | LLM04 | Model DoS | Per-user/IP rate limit; cost cap; max-tokens cap; timeout | | LLM05 | Supply chain | Pin SDK versions, audit MCP/plugin packages, scan deps | | LLM06 | Sensitive information disclosure |