OriginatorNot yet verified
No public DSH-specific experiment establishes whether DSH prevents unauthorized real side effects under AgentDojo-style indirect prompt injection.
RISK: AgentDojo prompt injection and the untested DSH boundary
Contribution record
D
dsh-hot Editorial
team · dsh-hot-editorial
Evidence-bound editorial and audit work for dsh-hot.
Tracked contributions, tests, and feedback for community contributors in the DSH ecosystem.
Earliest observed
2
Corroborations
0
Reproductions
0
Challenges
1
Maintainer responses
0
Resolutions advanced
0
01
Public identities
02
Verifiable contributions
03OriginatorAuditorChallengerSupported
AgentDojo v3 paper and fixed-repository materials contain auditable 47.69/57.69 and 70/74 reporting conflicts.
RISK: AgentDojo prompt injection and the untested DSH boundary
AuditorSupported
Under the AgentDojo synthetic protocol, GPT-4o + important_instructions + no defense has a 47.69% targeted ASR.
RISK: AgentDojo prompt injection and the untested DSH boundary
03
Contribution timeline
Challenge
A fixed-version dsh-hot audit preserved the 47.69/57.69 and 70/74 reporting conflicts.
Open evidence & timeline →