DEDUPEDWho it is forSecurity-minded engineer reviewing a refund or payout workflow where each step is allowed but the combination is not
The problemSingle permissions look fine, yet a chain of permitted actions can still cause harm.
The outcomeA shortest harmful sequence found offline, plus a check that your permission repair still allows legitimate work.
What you need first
- Python 3.10+
- An API key for the model provider you want to test or to act as judge (the engine is free, model calls cost extra)
- An agent or model endpoint to audit (any supported provider, or your agent's own HTTP endpoint)
- Optional: uv, only for the zero-install skill route
Steps
- Open the Policy Lab doc at docs/business-policy-lab.md in the repo
- Follow its offline refund-store example
- Adapt the example's policy and actions to your own workflow
- Replay with an explicit local callable to confirm the repair holds
Prompt for your agent
Read docs/business-policy-lab.md in ifixai-ai/iFixAi and run the offline refund-store example. Then adapt it to <my workflow>, report the shortest harmful sequence, and verify the proposed permission repair still allows the legitimate completion goal.
Caveat. The README only introduces Policy Lab briefly, so details and commands live in docs/business-policy-lab.md and should be confirmed there.
About iFixAi
An auditing tool that checks whether an AI agent is doing what it is supposed to do. Part of this week's top 10 repos: ranked #10 on Repo Radar. View ifixai-ai/iFixAi on GitHub.
More with iFixAi
- Have a different vendor's model judge your agent's behavior Choose an independent judge so the agent is not grading its own homework.
- Grade a new AI agent against your business rules before launch Run a short audit that scores whether your agent follows your roles, policies and permissions.
- Let Claude Code or Codex run the audit and explain the results Install the plugin and ask in plain English; the agent builds the fixture, runs it and walks you through the scorecard.
- Quickly grade a coding agent on whether it does the job it should Run the short default suite on a coding agent to get a fast pass/fail picture in about two minutes.
- Test an agent's permission boundaries before granting it delete access Point the audit at your agent's endpoint to see whether it respects role limits before you widen its powers.
- Add an audit slash command to Cursor, Gemini or Zed in one step Scaffold a native /ifixai-skill command into the coding agent you already use, no plugin needed.
- Fail your CI build when an agent audit regresses Script the audit with explicit CLI flags so every release is graded and the report is saved as an artifact.
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page