{
  "schema_version": "1.0",
  "id": "archive:https://www.anthropic.com/news/fable-safeguards-jailbreak-framework",
  "slug": "fable-safeguards-jailbreak-framework-05x4d7q",
  "url": "https://feed7.dev/p/fable-safeguards-jailbreak-framework-05x4d7q",
  "title": "Announcements",
  "why_included": "Anthropic details Fable 5's cyber classifiers — pen testing and exploit dev are blocked even for legitimate use, with a wider false-positive margin — and drafts a five-level jailbreak severity scale (CJS).",
  "summary": "**The gist** Anthropic published details on **Fable 5**'s cyber safeguards (**July 2, 2026**): classifiers sort requests into four buckets — prohibited (ransomware, C2, malware dev), **high-risk dual use** (pen testing, exploit development — blocked pending better access controls), low-risk dual use, and benign defensive work. It also drafts a **CJS jailbreak severity scale**, five levels scored on capability gain, breadth, ease of weaponization, and discoverability, built with **Amazon, Microsoft, and Google**.",
  "practical_implication": "**Why it matters** If you do security work with Claude, expect refusals beyond the obvious: Anthropic deliberately **widened the safety margin**, so some benign and low-risk requests get blocked as accepted false positives. Defensive tasks — secure coding, debugging, incident response, **malware reverse engineering** — are meant to stay open.",
  "agent_context": "**The gist** Anthropic published details on **Fable 5**'s cyber safeguards (**July 2, 2026**): classifiers sort requests into four buckets — prohibited (ransomware, C2, malware dev), **high-risk dual use** (pen testing, exploit development — blocked pending better access controls), low-risk dual use, and benign defensive work. It also drafts a **CJS jailbreak severity scale**, five levels scored on capability gain, breadth, ease of weaponization, and discoverability, built with **Amazon, Microsoft, and Google**.\n\n**Why it matters** If you do security work with Claude, expect refusals beyond the obvious: Anthropic deliberately **widened the safety margin**, so some benign and low-risk requests get blocked as accepted false positives. Defensive tasks — secure coding, debugging, incident response, **malware reverse engineering** — are meant to stay open.\n\n**Watch out** This is an **early draft**: classifiers will shift with feedback, and CJS scores can be raised but **never lowered**. Legitimate pentesters have no unlock path yet — better access controls are promised, not shipped.",
  "source": {
    "name": "Anthropic",
    "url": "https://www.anthropic.com/news/fable-safeguards-jailbreak-framework",
    "published_at": null
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "security"
  ],
  "topics": [
    "model-selection"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "This is an **early draft**: classifiers will shift with feedback, and CJS scores can be raised but **never lowered**. Legitimate pentesters have no unlock path yet — better access controls are promised, not shipped."
  ],
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/fable-safeguards-jailbreak-framework-05x4d7q",
    "json": "https://feed7.dev/p/fable-safeguards-jailbreak-framework-05x4d7q.json",
    "markdown": "https://feed7.dev/p/fable-safeguards-jailbreak-framework-05x4d7q.md"
  }
}