registry / claude-task-worker / 0.23.0

claude-task-worker@0.23.0

CLI tool that polls GitHub Issues/PRs and delegates work to Claude CLI

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

One or more suspicious static signals were detected.

Trigger

User runs a worker command such as `all`, `yolo`, or `usage`; `install` and `init` require explicit commands.

Impact

A configured worker can make unattended repository and GitHub changes; task output may be disclosed to the configured Slack destination.

Mechanism

GitHub-triggered autonomous Claude execution with optional Slack reporting and explicit plugin setup.

Rationale

Source inspection shows a real dangerous autonomous-agent capability and explicit first-party Claude plugin lifecycle action, but not concrete malicious or unconsented install-time behavior. Warn so users assess permissions, labels, prompts, and Slack destination before deployment.

Evidence

package.jsondist/index.js~/.claude/.credentials.json/tmp/claude-usage-cache.json.claude/worktrees.github/ISSUE_TEMPLATE/cc-triage-scope.yml.github/workflows/assign-creator-on-cc-triage-scope.yml

Network endpoints1

api.anthropic.com/api/oauth/usage

claude-task-worker@0.23.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code