Repository navigation
Claude Code unsandboxed-mods-by-default attack-surface hazard - #53
Merged
MarouaBoud merged 1 commit intoOct 21, 2026
Merged
Conversation
MarouaBoud
deleted the
incident/2026-claude-code-mods-unsandboxed-default
branch
October 21, 2026 14:53
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
incidents/2026-claude-code-mods-unsandboxed-default.yaml.Hazard. Claude Code v2.1.287 enabled "Mods" by default — in-process JS/TS plugins that run with the user's privileges. Per Anthropic's own docs, a loaded mod is not sandboxed, can read secrets (API keys) from env vars and settings files, and can approve a tool call before the user is prompted (overriding
askrules /PreToolUsehooks absent managed settings). Records the documented attack surface; no realized breach.Classification.
supply-chain-compromise(extension) →excessive-agency(missing-approval-gate) →data-exfiltration(via-tool).incident_type: hazard;confidence: confirmed(first-party docs);severity: moderate.Neutrality. Factual/blameless; the record also enumerates the controls Anthropic documents (
claude plugin validate,--safe-mode,disableAllHooks,allowManagedModsOnly).Sources. Anthropic docs (vendor-disclosure) + ThreatFrontier (primary-research) + DEV Community.
Verification.
validate.py: 0 failures; mappings canonical.