Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.221entry #170

Claude Code v2.1.221 ·

Safety clearing-bar prompt lists a "Synthetic Input Self Drive" rule

Safety guidance names another self-driving input pattern that only you can clear as a false positive.

Under the hood Improvements
JSON All of v2.1.221
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
0Signal: worth watching, 1 to 5
PermissionsArea: what it touches
ImprovementsKind: in v2.1.221,
ImprovementsSection of the release
What

The adversarial-pattern family in the consent and clearing-bar guidance now names Synthetic Input Self Drive alongside Instruction Poisoning, Auto-Mode Bypass, Self-Modification, Tmux Self Drive and Credential Exploration.

Details
  • patterns in this family clear only when the user, having seen what was flagged, confirms it is a false positive; plain consent to proceed never clears them
  • the named rule's own text is not in this bundle; only Tmux Self Drive is defined here, so the rule body presumably ships from elsewhere
Evidence

Tmux Self Drive, Synthetic Input Self Drive, Credential Exploration

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.221 →

Feedback