anthropics / anthropics/claude-code

[Bug] Cybersecurity classifier blocking defensive malware analysis tooling mid-conversation

Aperta
#88,014 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub
area:model area:security bug platform:macos stale
Lingua principale
Python
Stelle
145k
Fork
23.1k
Metriche di merge delle PR
Metriche PR in attesa

Descrizione

**Bug Description**
A conversation building defensive Android malware triage tooling (static APK analysis, permission auditing, LLM-assisted classification via Ollama Cloud, passive OSINT for IOC reporting to law enforcement) was blocked by the cybersecurity safety classifier partway through. The conversation had been proceeding normally for ~15 turns with no prior flags, including file creation of manifest audit code, router logic, and LLM client wrapper — all deterministic/defensive in nature.

Context:

Use case: triaging a real fake-KYC banking-dropper APK received via a compromised family member's WhatsApp, for submission to Maharashtra Cyber / CERT-In.
Explicit scope boundary was documented in the project README (passive analysis and OSINT only; active exploitation of attacker infrastructure explicitly excluded).
No malware was requested to be written; only detection/analysis tooling.
The block occurred on a message continuing prior technical work, not on a new/escalated request.

What I'd like investigated:

Whether this pattern (multi-turn defensive tooling requests, code generation for static analysis) is a known trigger for over-blocking.
Whether Cyber Verification Program enrollment status is correctly checked/applied mid-conversation, or only at session start.

Attachments available on request: conversation transcript, repo scaffold created prior to the block.

**Environment Info**
- Platform: darwin
- Terminal: iTerm.app
- Version: 2.1.212
- Feedback ID: 2fb7f73d-2023-4568-bb31-44c16e6f03ec

**Errors**
```json
[]
```

Guida per i contributori

Nessuna guida per i contributori indicizzata per questo repository

Direzione di ricerca

Start with the supplied conversation transcript and repo scaffold, especially the README scope boundary and the manifest audit, router, and LLM client wrapper mentioned in the report. Reproduce or review the block if the materials are provided, then determine whether defensive multi-turn requests trigger over-blocking and whether Cyber Verification Program enrollment is applied mid-conversation; done means both questions have a documented finding.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Valutazione

Stack tecnologico
android, ollama, python
Ambito
ai, devtools, security
Tipo di issue
Bug
Difficoltà
4/5
Tempo stimato
3-5 giorni
Stato di attività
Attiva
Chiarezza
Da chiarire
Idoneità per principianti
35/100

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.