Stolen Token Replay

Simulated: every actor below is a script with fake tokens. No real agent, service, or standard is used.

1. Choose the defenses

A change resets the demo.

The token names one API. Other APIs refuse it. Real: RFC 8707

The token ties to the host's key. Each call needs a signed proof. Real: RFC 9449 (DPoP)

The token says "do not log". Log tools remove it. Proposal, not a standard

Token claims (fake) Illustration


          

2. Leak it, then replay it

Press "Leak the token" to start.

Replay lanes An identity provider issues a token to an agent host. The host calls an API gateway. The host log goes to GitHub. An attacker copies the log line and replays the token at the gateway. The page shows accept or reject on each lane. 1 issue 2 call 3 log 4 copy 5 replay Identity provider Agent host API gateway Attacker Public log

3. Event log

No events yet.

    What the gateway sees

    The last request and the checks it met.

    No request yet.

    Pain point

    A leaked agent token works for anyone who finds it.

    Problem statement

    Agent tokens leak into logs. Anyone who copies one can replay it at the gateway. The team must then rotate every credential the token could reach.

    What sparked it

    Per public reports, LiteLLM 1.107.0 was a poisoned release on 2026-10-21. LiteLLM says stolen tokens likely came from gateway logs.

    Why this approach

    Each defense stops a different step of the replay. The ideas come from RFC 8707 and DPoP (RFC 9449).

    Hypothesis tested

    We believed that a token bound to one audience and one key is useless to a thief. If it holds, a replay fails at the gateway.

    How to try it

    1. Open the Prototype tab and pick zero to three defenses.
    2. Press "Leak the token".
    3. Press "Replay it".
    4. Read the event log.

    What this does not do

    Notes

    Sources

    Traces

    Prompts used to make this prototype
    StepPromptModelToolDate

    Cost

    Cost to make this prototype
    StepModelInput tokensOutput tokensCost (USD)
    Total

    Measured: the author runs used 105,911 tokens in total. Estimated: the split into input and output tokens (90 percent input, 10 percent output) and the dollar cost, at $2 input and $10 output per million tokens for Sonnet 5.5 (about $0.30). The run reported one total only. The lead session's planning, research, and publishing are not included. The prompts in the Traces section are listed in the order they were given.