registry / stratless / 0.3.4

stratless@0.3.4

Give your AI coding assistant a model of who you are — read from your own history — so it stops making you feel stupid. Local, private, no account.

AI Security Review

scanned 8h ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. The CLI explicitly manages Claude Code configuration and, with `init --auto`, installs a persistent Stop hook that refreshes its profile after sessions. No unconsented install-time mutation or concrete malicious payload was found.

Static reason

No blocking static signals were detected.

Trigger

User runs `stratless init --auto`, `stratless update`, or `stratless stop`.

Impact

Can retain transcript copies, alter Claude Code settings, and cause background profile refreshes after user sessions.

Mechanism

Explicit Claude Code profile and lifecycle-hook management.

Rationale

Source inspection confirms consent-gated but persistent Claude Code configuration and lifecycle-hook behavior. Per policy, first-party agent extension setup warrants a warning, not a publish block, absent exfiltration or unconsented install-time mutation.

Evidence

package.jsondist/init.jsdist/sink.jsdist/index.jsdist/notify.jsdist/claude.js~/.claude/settings.json~/.claude/projects/**/*.jsonl~/.stratless/archive/*~/.claude/HUMAN.md~/.claude/CLAUDE.md~/.stratless/notify.json

Network endpoints1

registry.npmjs.org/stratless/latest

stratless@0.3.4

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code