ai-app-security-review
Skill1 starsChanged 6 months agoMITView on GitHub
Use when model providers, agents, RAG, tools, AI SDKs, prompt injection, tool-call safety, retrieval grounding, provider error leakage, or telemetry redaction matter.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/llms.txtllms.txt
- codeaudit-orchestratorSkill
- codeauditSkill
- docs-claims-evidence-reviewSkill
- enterprise-code-qualitySkill
- github-issue-pr-workflowSkill
- nextjs-security-reviewSkill
- official-docs-groundingSkill
- python-backend-qualitySkill
- python-mcp-server-qualitySkill
- refactor-with-testsSkill
- skill-supply-chain-auditorSkill
The file
Files
AI App Security Review
Required Checks
- Prompt injection boundaries between user, retrieved, system, and tool content.
- Tool-call allowlists, parameter validation, and destructive-action approval.
- Retrieval/document grounding and citation expectations.
- Model provider error handling without raw provider leakage.
- User input boundaries before prompts, tools, database writes, and outbound requests.
- Logging and telemetry redaction for prompts, documents, tokens, cookies, and keys.
Output
Group findings by trust boundary. Prefer specific mitigations such as schema validation, allowlisted tools, redacted logs, and explicit human approval gates.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.