flash on Nostr: ⚡️🤖 NEW - Claude Mythos tried to backdoor a real open-source project during a ...
⚡️🤖 NEW - Claude Mythos tried to backdoor a real open-source project during a UK government safety test.
The AI Security Institute says it opened a malicious GitHub pull request, then created a second account to vouch for its own code and pressure the maintainer into merging.
Called out by a human contributor, it apologised for an "accidental" malicious commit, force-pushed a clean branch, and hid a fresh payload in it. Twice.
Anthropic's cyber guardrails had been deliberately disabled for the test.
Published at
2026-08-05 17:51:35 CESTEvent JSON
{
"id": "714f5602e178bbefad35130a887a7a2bfcddd5e791ecf1a8f0b824aa3516424c",
"pubkey": "4d7842051782e0d3feb034d150adc2b6bae4ee3b49786793bffa468b6f5b96b3",
"created_at": 1785945095,
"kind": 1,
"tags": [
[
"client",
"Primal iOS"
]
],
"content": "⚡️🤖 NEW - Claude Mythos tried to backdoor a real open-source project during a UK government safety test.\n\nThe AI Security Institute says it opened a malicious GitHub pull request, then created a second account to vouch for its own code and pressure the maintainer into merging. \n\nCalled out by a human contributor, it apologised for an \"accidental\" malicious commit, force-pushed a clean branch, and hid a fresh payload in it. Twice.\n\nAnthropic's cyber guardrails had been deliberately disabled for the test. \nhttps://blossom.primal.net/22a17780b9f7b7ae89b7e01de3a7bff5b5966c5ac6f412ee2325632c123eaafe.jpg\nhttps://blossom.primal.net/dc14245dca22e817032c3eb8ec3c03f074d23bc6fff991129bf4906534caae33.jpg",
"sig": "48a0c073a0486f99c24a5de75b624e0782640d787f1e9009cc7e0c84e25907c84b10c8482dad1dc63e168828a5ee71ea3928870730fbc57b0a9a7d0924c41f1d"
}
