registry / claude-task-worker / 0.21.0

claude-task-worker@0.21.0

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` or `yolo`; `install` is an explicit user command.

Impact

Labeled repository tasks can cause an unattended, permission-skipping Claude session to modify the selected repository; configured Slack receives task status/output.

Mechanism

GitHub-driven autonomous Claude execution with optional Slack reporting.

Rationale

No lifecycle hook or covert exfiltration chain establishes malicious package behavior. The package nevertheless exposes a high-impact autonomous agent workflow that executes Claude with permissions skipped and can report output to a configured webhook.

Evidence

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

Network endpoints2

api.anthropic.com/api/oauth/usagehooks.slack.com/services/xxx/yyy/zzz

claude-task-worker@0.21.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code