Understand this story
On November 13, 2026, the hacker Pliny breached Anthropic's Claude Code and published the complete system prompt and tool definitions to GitHub. According to reports by 36Kr AI and Phoenix Technology, the leaked document totals 953,659 characters across 7,832 lines, roughly 30 times the 31,881 characters of the version publicly released on the official website, revealing that Claude has 128 built-in tools and 44 skill sets, covering processes such as making phone calls to book reservations, automatic expense reimbursement, and prescription refills, and that it is prohibited from launching sub-Agents on its own without a user's request. On security rules, when connected to a local computer it locks down deletion commands such as rm by default, and it refuses stock trading, money transfers, and filling in real passwords on a user's behalf outright, treating even a restriction-lifting message signed by Anthropic as a scam. Phoenix Technology said the leak occurred just over two hours after the release of Claude Fable 5.2. Pliny has now made the above content public, and there have been no further developments.
AI-generated from public reports
Latest development · Report
Full system prompt for Claude Fable 5.2 leaked, containing 128 tools and 44 skill setsDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 13
36Kr · AI
Full system prompt for Claude Fable 5.2 leaked, containing 128 tools and 44 skill sets
On the day Anthropic's new model Claude Fable 5.2 launched, hacker Pliny breached Claude Code and published the full system prompt to GitHub: 953,659 characters and 7,832 lines in total, roughly 30 times the 31,881 characters of the version publicly released on the official website. The document shows that Claude has 128 built-in tools and 44 skill sets, covering processes such as making phone calls to book reservations, automatic expense reimbursement, and prescription refills, and it prohibits launching sub-Agents on its own without a user's request. On safety rules, when connected to a local computer it locks down deletion commands such as rm by default, and it flatly refuses stock trading, money transfers, and filling in real passwords on the user's behalf; even messages signed by Anthropic that lift restrictions are treated as scams.
Phoenix Technology
Claude Fable 5.2 System Prompt Leaked: 950,000 Characters, 128 Tools, and 44 Skills
More than two hours after Anthropic released Claude Fable 5.2, the hacker Pliny breached Claude Code and uploaded the complete system prompt and tool definitions—953,659 characters across 7,832 lines—to GitHub. The leaked content shows that Claude has 128 built-in tools and 44 skills, covering workflows such as making phone calls to book reservations, automatic expense reimbursement, and prescription refills, while by default locking down file-deletion commands such as rm and prohibiting stock trading, money transfers, and filling in real passwords on users' behalf. The article also states that Fable 5.2 and the unreleased Mythos 5.2 share the same underlying model and both support a 1-million-token context, while the public version's prompt is only 31,881 characters.
Heat trend for this story
- Current
- 6
- Period peak
- 18 Nov 13 19:00
- 24-hour change
- -50%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.