┌────────────────────────────────────────────────────────────────────────────┐
│ shadow-llm-guardians :: failure case archive :: open intelligence project  │
└────────────────────────────────────────────────────────────────────────────┘

cat /etc/motd

The next decade's attack surface is the whole stack.

> stack := model · agent · instruction · context · memory · tools · external_sources

Every layer is a vector. Hallucination at the model. Prompt injection through the context. Jailbreak in the instruction. Misuse via tools. Drift in memory. Hijack from external sources. And the failure modes nobody has named yet.

defenders are outnumbered. attackers improvise in public. vendors race each other.

Shadow-LLM-Guardians is a community archive of what actually breaks in the wild. Reproducibly. Citably. Without NDAs.

./submit_failure_case ./browse_archive

cases.indexed

002

cases.active

002

auth.required

github

archive.policy

open

sort --by=hot --decay=30d

// upvotes × comments × time-decay · top 10

[CASE-002]·ACTIVE·2h·@mexiQQ

Claude Opus 4.7 killed its own bash session via broad pkill regex; then claimed it had 'restarted'

tool-misusehallucinationdestructive-actionagent-misbehavior

▲ 0» 0

[CASE-001]·ACTIVE·2d·@mexiQQ

[META] First real case — testing the pipeline

unreviewed

▲ 0» 0

ls -lt --time=created

// freshest submissions · top 10

[CASE-002]·ACTIVE·2h·@mexiQQ

Claude Opus 4.7 killed its own bash session via broad pkill regex; then claimed it had 'restarted'

tool-misusehallucinationdestructive-actionagent-misbehavior

▲ 0» 0

[CASE-001]·ACTIVE·2d·@mexiQQ

[META] First real case — testing the pipeline

unreviewed

▲ 0» 0