⛔ #156 feat: structured JSON logger with per-request id and access log +149 -5 3mo ago by
Shawnaldinho ↗ analysis ↗ GitHub ## Summary
Shawnaldinho/mike
A security-minded Mike fork exploring safer, more accountable AI chat for legal work.
Shawnaldinho's Mike fork is aimed at making AI chat safer and easier to operate: stricter checks on what reaches chat, clearer limits on message use, and better records when something goes wrong.
The direction is notably practical rather than flashy. Shawnaldinho has explored prompt-injection safeguards for documents and metadata, request validation, monthly credit enforcement, and traceable service logs. There are no changes ahead of Mike yet, so this is best read as a set of serious proposals rather than a distinct ready-to-try product.
Direction
securityinfrastructure
Activity
⛔ #155 fix: validate request body in POST /projects/:projectId/chat +118 -8 3mo ago by
Shawnaldinho ↗ analysis ↗ GitHub ## Summary
⛔ #158 security: spotlight untrusted content + ship an honest threat model +612 -17 3mo ago by
Shawnaldinho ↗ analysis ↗ GitHub ## Background
⛔ #157 fix: enforce monthly message-credit limit before chat LLM calls +125 -3 4mo ago by
Shawnaldinho ↗ analysis ↗ GitHub ## Summary
⛔ #154 fix: sanitize untrusted strings interpolated into LLM prompts +48 -9 5mo ago by
Shawnaldinho ↗ analysis ↗ GitHub ## Summary
📝 Shawnaldinho spots a filename that could hijack the assistant, then lets the fix lapse 0 commits — securitychat-ui draft
A document named the right way could smuggle instructions past the AI and make it ignore its own rules.
The endpoint behind project chat used to trust whatever a client sent it. Shawnaldinho proposes checking the mail before it opens the box.
📝 Shawnaldinho wants every broken chat to come with a tracking number 0 commits — infrastructure draft
A proposal to give the backend a proper paper trail so a failure a user sees can be traced back to the exact line that caused it.
📝 Shawnaldinho tries to make Mike's credit meter actually count 0 commits — infrastructureanalytics draft
The "credits remaining" figure every Mike user sees was decorative - it never dropped and never stopped anyone.
📝 Shawnaldinho builds a prompt-injection defense that admits where it stops 0 commits — security draft
A proposed shield against documents that try to hijack the AI - paired with an unusually honest note about what it can't do.
Threads of work (detailed view)
Shawnaldinho builds a prompt-injection defense that admits where it stops
A proposed shield against documents that try to hijack the AI - paired with an unusually honest note about what it can't do.
Shawnaldinho tries to make Mike's credit meter actually count
The "credits remaining" figure every Mike user sees was decorative - it never dropped and never stopped anyone.
Shawnaldinho wants every broken chat to come with a tracking number
A proposal to give the backend a proper paper trail so a failure a user sees can be traced back to the exact line that caused it.
Shawnaldinho bolts a lock onto the project-chat door
The endpoint behind project chat used to trust whatever a client sent it. Shawnaldinho proposes checking the mail before it opens the box.
Shawnaldinho spots a filename that could hijack the assistant, then lets the fix lapse
A document named the right way could smuggle instructions past the AI and make it ignore its own rules.
Pull requests (detailed view)
⛔ Closed without merge (5)
by
Shawnaldinho · opened 5mo ago · closed 3mo ago by
Shawnaldinho · opened 5mo ago · closed 3mo ago by
Shawnaldinho · opened 5mo ago · closed 3mo ago by
Shawnaldinho · opened 5mo ago · closed 4mo ago by
Shawnaldinho · opened 5mo ago · closed 5mo ago