Evidence · DiggingBeagle record
Shibboleth honeypot identifies agent models and harnesses from controlled behavioral traps, without successful prompt injection
Original Shibboleth paper evaluates honeypot traps using declarations and behavioral telemetry to infer model and harness identity in a closed candidate set. Its roughly 90% identification rates cannot be used to identify a real criminal operator or guarantee open-world attribution.
- Source role
- primary disclosure
Evidence record
Original Shibboleth paper evaluates honeypot traps using declarations and behavioral telemetry to infer model and harness identity in a closed candidate set. Its roughly 90% identification rates cannot be used to identify a real criminal operator or guarantee open-world attribution.
Claim-level citations (1)
- supportsShibboleth fingerprinted agent models from deceptive task behavior, not prompt-injection success: Shibboleth reports roughly 90% to 92% top-1 agent-model identification within its closed evaluation and warns that such fingerprints do not identify a real-world attacker.
Section 7 Results, combined declarative and behavioral traps, threat-model limitations