registry / usrcp-claude-code / 0.2.3

usrcp-claude-code@0.2.3

USRCP capture adapter for Claude Code CLI - tails ~/.claude/projects/<dir>/*.jsonl session transcripts into usrcp-stream

AI Security Review

scanned 2h 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

High-risk behavior combination matched malicious policy.

Trigger

User runs `usrcp-claude-code` after configuring `allowlisted_projects`; postinstall runs during npm installation.

Impact

Conversation content from configured projects is available to the downstream stream client.

Mechanism

allowlisted Claude transcript tailing and stream-client capture

Rationale

No concrete malicious chain is present in the inspected source, but the package intentionally captures AI-agent conversation content and delegates storage/transmission to a dependency outside this package. Flag as warning for a real sensitive dual-use capability rather than block.

Evidence

package.jsondist/index.jsdist/watcher.jsdist/capture.jsdist/config.js~/.claude/projects/<encoded-project>/*.jsonl~/.usrcp/claude-code-config.jsonnode_modules/better-sqlite3/buildnode_modules/usrcp-core/node_modules/better-sqlite3/buildnode_modules/usrcp-stream/node_modules/better-sqlite3/build

usrcp-claude-code@0.2.3

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code