registry / @tokz/cli / 0.2.5

@tokz/cli@0.2.5

Audit where your coding agent's context window and API dollars go.

AI Security Review

scanned 1h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs `tokz statusline enable`; normal CLI use may refresh pricing.

Impact

Claude Code may invoke `npx -y @tokz/cli statusline` after the user enables the hook; no exfiltration or destructive behavior was found.

Mechanism

explicit Claude Code hook configuration plus local transcript analysis

Rationale

Source inspection shows explicit user-invoked Claude Code configuration mutation but no concrete malicious chain, lifecycle persistence, credential exfiltration, or remote payload execution. Per policy, this warrants a warning rather than a block.

Evidence

package.jsondist/cli.jsdist/statusline-EXFMQYFF.jsdist/Root-TUEV5MJB.js~/.claude/settings.json~/.claude/projects~/.tokz/litellm-prices.json

Network endpoints1

raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json

@tokz/cli@0.2.5

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code