I built a tool to stop AI coding agents from leaking my secrets(github.com)

Curious how this handles the case where the agent legitimately needs a key to test something against a real API. We hit this when wiring up Zendesk and Intercom flows for the bot pipeline, and the team kept pasting tokens into prompts because the masking layer broke the integration test. Does yours proxy the call or just redact on output?

Curious how this handles structured data leaks, not just env vars. In my line of work the bigger risk is an agent pasting client names or matter numbers into a third party API, which no regex for AWS keys is going to catch. Does it support custom patterns or is it focused on the standard credential formats?

Curious what the threat model is here. Most leaks I've seen in client work come from agents echoing env vars into chat logs or commit messages, not from anything fancy, and a pre-commit hook plus a scoped .env covered 90% of it for a 12 person team.

Curious how this handles the gap between secrets and just sensitive context, since in my classroom pilots half the leakage risk is student names and grades getting pasted into prompts, not API keys. Does it cover anything beyond pattern-matched credentials?

We solved this less elegantly by just running agents in containers with a scrubbed env and a vault proxy that injects secrets only at runtime. Curious what your detection layer looks like, since the painful cases for us were never .env files but secrets pasted into chat history or accidentally echoed in test output.

Curious how this compares to just running agents in a devcontainer with a scrubbed env and a pre-commit hook for secret scanning. We went that route after one of our agents helpfully pasted a Stripe key into a GitHub issue, and the friction has been close to zero since.

Interesting, though my paralegal angle on this is different: the secrets I worry about leaking aren't API keys, they're client names and case facts in prompts. Does your tool do anything for plain-text PII in agent context, or is it strictly env vars and credentials?

we mandated dotenv-vault after an intern's agent pasted prod keys into a gist