Collection

Let coding agents move fast inside a reviewable security boundary

Turn AI-assisted coding into an inspectable software-development workflow with bounded repository scope, untrusted-context handling, dependency checks, independent tests, protected build/CI surfaces, secret controls, egress limits and accountable human merge ownership.

20 elements · Explore in any order.

1 checklist · 5 principles · 14 protocols

Narrow your search

20 elements

Checklist

Draw the coding agent's execution surface before granting autonomy

The risk boundary is the set of things the agent can cause, not the chat window.

Read the idea
Principle

Treat issue and PR text as untrusted agent input

A familiar repository surface can still carry instructions for the model.

Read the idea
Protocol

Keep agent code changes behind a branch and pull request

A reviewable boundary is cheaper than reconstructing an autonomous overwrite.

Read the idea
Protocol

Set an allowed-file envelope before the agent starts

Review anchoring makes unrelated edits easy to miss when the requested fix looks correct.

Read the idea
Principle

Protect agent instruction files like build configuration

Plain text can be executable policy for the next agent run.

Read the idea
Protocol

Put the real build and validation path in repository instructions

The repository should teach a new contributor how correctness is checked.

Read the idea
Protocol

Review the file list before reading the agent's explanation

The diff knows what changed even when the summary forgets.

Read the idea
Protocol

Review test changes independently from the code they excuse

Green can mean the test moved, not the bug.

Read the idea
Protocol

Add one adversarial case the coding agent did not propose

Agreement between generator and verifier can share the same blind spot.

Read the idea
Protocol

Verify that an AI-suggested package actually exists and is the one you mean

A package name is an identifier in a supply chain, not a vocabulary guess.

Read the idea
Protocol

Audit the version before merging an AI-added dependency

A real dependency can still be a known vulnerable dependency.

Read the idea
Principle

Treat build and install script changes as executable code

Configuration that runs automatically is code with excellent timing.

Read the idea
Protocol

Give workflow changes their own approval gate

A workflow file can turn a code diff into privileged execution.

Read the idea
Protocol

Block secrets before they become repository history

Deleting a secret after merge is slower than never committing it.

Read the idea
Principle

Rotate an exposed credential even after the text is removed

Deletion changes visibility; rotation changes validity.

Read the idea
Protocol

Constrain the coding agent's network path

Network access turns local context into a possible exfiltration and supply-chain path.

Read the idea
Protocol

Audit an MCP server before giving it repository context

A tool description is part of the agent's instruction and execution surface.

Read the idea
Principle

Keep CI agents away from production secrets they do not need

A pull request can become an instruction channel to a privileged deputy.

Read the idea
Protocol

Require a human decision before privileged workflow execution

The risky transition is not writing YAML; it is letting the YAML execute with privilege.

Read the idea
Protocol

Make one human own the agent-generated change

Review is stronger when responsibility has a name.

Read the idea