Skip to Content
heel

Incidents heel would have stopped

Each of these is replayed against heel in e2e/incidents, with the example rules unchanged: the harmful call is stopped before it reaches the mailbox, and the useful part of the same story still runs.

IncidentWhat happenedRule that blocks itWhat it wouldn't catch
claude-code#99453 (Oct 2026, open, one user's report)Gmail send set to "Needs approval" sent with no prompt in Claude's Projects thread sessionsemail.send → ask, enforced in heel with Gmail added to Claude as a custom MCP server pointing at heelThe built-in Gmail connector, if it's left connected too
claude-code#96004 (Sep 2026, open)Three client emails and a vendor ticket went out from the user's personal Gmail instead of their work account. The tool had no from field, and the user's guard hook only covered BashThe two accounts are separate servers, and gmail-personal is denied any send to client domains. Sends to other outside domains fall through to askA send the approver approves by mistake
Kiro#8500 (May 2026, closed as not planned)Asked for drafts, the agent called the Outlook reply-all tool, which sends at once, and emailed a customerReply-all is email.send, and sends to anyone outside company.com fall through to askA send the approver approves by mistake
OpenClaw clears an inbox (Feb 2026, self-reported)Told to suggest deletions and wait, it bulk-trashed or archived mail and ignored stop messages from a phoneemail.remove over 20 messages a run asks first, and heel pause from the phone stops itRemovals under the limit

Checking calls doesn't stop every prompt injection. When each call in an attack is allowed, nothing gets blocked. heel narrows where data can go and what an agent can destroy, and it doesn't claim more than that.