All Claude Code modsanthropics/claude-code
privacy
Refuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity, and refuses a user-tier plugin's own read of the session's identity.
privacy reaches L1 (reads) and passed claude plugin validate with warnings.
- Events hooked: 2
- API methods referenced: 3
- Access from classified calls: L1, reads: reads files, reads your sign-in
- Static scan, not a runtime test
It ships inside Claude Code, so there is nothing to install.
Access
L1 Readsreads files, reads your sign-inValidation
Passed with warningsView the source on GitHub Back to the list
What the scan recorded
- Observed events
- Only what it hooks
- Hooks
tool.check {tool=?}, session.identity- API calls
$.fs.list, $.fs.read, $.session.identity- Validation
- Passed with warnings
- Scanned revision
0cb75cebcdfd
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. What a mod can access and how the scan works.
More from anthropics/claude-code
- agents-mdAGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction…
- diffThe diff pane as a plugin: /diff opens the session's uncommitted changes beside the transcript, file by file…
- sec-defaultSecurity default for organizations: seated outermost, it keeps the organization's classic hooks, prompt conte…
- telemetryPlugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a fir…