Claude Code Wingman

SuspiciousAudited by ClawScan on May 10, 2026.

Overview

The skill is mostly coherent, but it can run persistent Claude Code sessions, auto-approve sensitive tool requests, and use local Clawdbot/WhatsApp authority, so it needs review before use.

Only install this if you trust the author and are comfortable letting it orchestrate Claude Code on your local projects. Prefer interactive approvals, avoid --auto and 'always' unless the project is fully trusted, use dedicated work directories, monitor active tmux sessions, and stop any background monitor when finished.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Claude Code may be allowed to run commands or modify project files without you seeing and approving each action.

Why it was flagged

The auto-approver automatically answers Claude Code permission prompts with an allow-for-session/project selection, which can authorize file edits, shell commands, or other tool actions without per-action user review.

Skill content
elif echo "$OUTPUT" | grep -q "Do you want"; then ... # Option 2 is typically "Yes, and allow for session/project" ... tmux send-keys -t "$SESSION_NAME" Down Enter
Recommendation

Keep interactive approval as the default, avoid using --auto or 'always' except in tightly trusted projects, show the full requested command/file change before approval, and consider disabling automatic trust/tool approvals.

What this means

A local process could potentially spoof an approval or force an 'always approve' response for a Claude Code session.

Why it was flagged

Approval decisions are passed through predictable files under /tmp without explicit private-directory permissions, ownership checks, or a nonce. Code running as the same user, including untrusted project code, could potentially read pending prompts or write an approval response.

Skill content
APPROVAL_DIR="/tmp/claude-approvals" ... RESPONSE_FILE="$APPROVAL_DIR/${SESSION_NAME}.response" ... RESPONSE=$(cat "$RESPONSE_FILE") ... always|2) ... tmux send-keys -t "$SESSION_NAME" Down Enter
Recommendation

Use a per-user private runtime directory with 0700 permissions, chmod approval files to 0600, validate file ownership, and include an unpredictable token/nonce before acting on a response.

What this means

Installing/running the monitor gives the skill access to local Clawdbot notification authority, even though this credential use is not clearly declared in the registry metadata.

Why it was flagged

The notification helper reads the local Clawdbot config to obtain a webhook token and phone number, then uses that delegated authority to send WhatsApp messages. The registry metadata declares no required env vars, config paths, or primary credential.

Skill content
CLAWDBOT_CONFIG="${CLAWDBOT_CONFIG:-$HOME/.clawdbot/clawdbot.json}" ... WEBHOOK_TOKEN=$(jq -r '.hooks.token // empty' "$CLAWDBOT_CONFIG" ... ) ... -H "Authorization: Bearer $WEBHOOK_TOKEN"
Recommendation

Declare the Clawdbot config path and webhook token requirement, document exactly what is sent, and use a minimally scoped token dedicated to notifications if possible.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

The monitor can continue running in the background, watching sessions and sending reminders after the initial task is started.

Why it was flagged

The package includes a long-running daemon that continuously monitors tmux sessions and sends approval notifications. This is aligned with the stated purpose, but users should know it persists until stopped.

Skill content
# master-monitor.sh - Master daemon that monitors all Claude Code sessions ... while true; do ... sleep "$POLL_INTERVAL" ... done
Recommendation

Provide clear start/stop commands, restrict monitoring to Wingman-created sessions, and stop the daemon when remote approval monitoring is no longer needed.

What this means

You may run code that differs from the reviewed registry artifact if the remote repository changes.

Why it was flagged

The manual installation path pulls executable shell scripts from a mutable GitHub repository without a pinned commit or checksum. That is common for developer tools, but it is a provenance gap.

Skill content
git clone https://github.com/yossiovadia/claude-code-orchestrator.git ... chmod +x *.sh lib/*.sh
Recommendation

Install from a pinned release or commit, review the scripts before chmod/execution, and keep the registry metadata aligned with required binaries such as jq/curl.