team-dev@0.1.4
VERIFIED· install onlyPublisher claims: "Multi-agent development team orchestration. Use when managing coding agents (Codex, Claude Code, Gemini, Cursor) for automated software development: (1) Spaw..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 23 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
del_proc = subprocess.run(['git', 'branch', '-d', branch], cwd=repo_path, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(['git', 'worktree', 'remove', '--force', worktree], cwd=repo_path)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.pr_check = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(['git', 'worktree', 'remove', '--force', worktree], cwd=repo_path)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["tmux", "kill-session", "-t", session], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(["gh", "auth", "status"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.pane = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(['git', 'branch', '-D', branch], cwd=repo_path, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(["tmux", "has-session", "-t", session], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(["gh"] + gh_args, capture_output=True, text=True, cwd=cwd)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.pr_check = subprocess.run(["gh", "pr", "list", "--head", branch], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(['git', 'branch', '-D', branch], cwd=repo_path, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.agent['cancelledAt'] = int(subprocess.run(['date', '+%s'], capture_output=True).stdout.strip()) * 1000Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.kill -KILL "$_cmd_pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "$_watch_pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if [[ -n "$lock_pid" ]] && ! kill -0 "$lock_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if kill -0 "$_cmd_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.agent['cancelledAt'] = int(subprocess.run(['date', '+%s'], capture_output=True).stdout.strip()) * 1000Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.kill -TERM "$_cmd_pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.has_session = subprocess.run(['tmux', 'has-session', '-t', session], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(['tmux', 'kill-session', '-t', session], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run([cmd, "--version"], capture_output=True, text=True, timeout=4)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["tmux", "kill-session", "-t", probe_session], capture_output=True, text=True, timeout=2)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.