Haseeb reports surprise that prompt injection attempts via cold email are not more common given OpenClaw adoption, implying a growing security surface as agents ingest untrusted inbound content.
Has anyone seen prompt injection cold email attempts in the wild?
Surprised this isn't more of a thing now that OpenClaw is all over the place.
This finding is one of many signals tracked across Indiehacking. The live feed updates every few hours with new expert voices, debates, and emerging ideas.
← Back to Indiehacking