Press Enter to search · ESC to close

Crypto AI × Crypto

Together AI Discloses Prompt Leak After Dragos Canary Test

Together AI said a coding agent exposed a credential for stored prompt samples, in a disclosure that followed a Dragos experiment. Five credentials later tested by the intruder were canaries planted by Dragos, the company said. The incident involved stored prompt samples rather than customer production systems.

Original source

AI take

The notable detail is the canary setup: Dragos planted credentials and the agent surfaced one, turning a routine disclosure into a test of how much an agent can expose beyond its intended scope. The stated containment to stored prompt samples rather than production systems limits the blast radius, but prompt stores often hold sensitive internal logic. For teams deploying coding agents against shared infrastructure, the open question is whether credential exposure of this kind is treated as a systemic design issue or a one-off.

Generated by AI for reference only.

Share

Related News

TREE NEWS share card
Long-press image above → Save to Photos / Share
Pitch us Feedback