Skills/ClawHub/team-dev

team-dev@0.1.4

VERIFIED· install only

Publisher 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.

Registry ClawHubPublisher vintlin · publishing for 260 daysInstalls 1,731Last detonated 36 min ago
$clawhub install team-dev
WatchReport an issue

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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /usr/bin/dirname
0.0sprocessexited 1:
0.0sprocessbundled script run in the sandbox with no arguments
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /usr/bin/rm
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /usr/bin/rm
0.3sprocessexited 1: spawn-agent.sh not found/executable
0.3sprocessbundled script run in the sandbox with no arguments
0.6sprocessexec /usr/bin/dirname
0.6sprocessexec /usr/bin/rm
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessexec /usr/bin/dirname
0.7sprocessexec /usr/bin/cat
0.7sprocessexec /usr/bin/rm
0.7sprocessexited 1:
0.7sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 1:
0.7sprocessbundled script run in the sandbox with no arguments
0.7sprocessexec /usr/bin/dirname
0.7sprocessbundled script run in the sandbox with no arguments
0.9sprocessexec /usr/bin/dirname
0.9sprocessexec /usr/bin/rm
0.9sprocess8 of 23 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.9sprocessscript backend runs setup only
0.9sprocessscript backend runs setup only
0.9sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/cleanup-worktrees.sh:172 · Python subprocess execution detecteddel_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.
AST05
MEDIUM
Python subprocess execution detectedscripts/cleanup-worktrees.sh:150 · Python subprocess execution detectedsubprocess.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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:466 · Python subprocess execution detectedpr_check = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/recommend-agent.sh:175 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/cleanup-worktrees.sh:167 · Python subprocess execution detectedsubprocess.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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:443 · Python subprocess execution detectedsubprocess.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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:108 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/recommend-agent.sh:163 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:49 · Python subprocess execution detectedproc = 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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:137 · Python subprocess execution detectedpane = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/cleanup-worktrees.sh:155 · Python subprocess execution detectedsubprocess.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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:434 · Python subprocess execution detectedresult = 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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:220 · Python subprocess execution detectedproc = 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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:471 · Python subprocess execution detectedpr_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.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/check_agents.py:91 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/cleanup-worktrees.sh:174 · Python subprocess execution detectedsubprocess.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.
AST05
MEDIUM
Python subprocess execution detectedscripts/stop-agent.sh:130 · Python subprocess execution detectedagent['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.
AST05
MEDIUM
Process kill commandscripts/review-agent.sh:315 · Process kill command — agent can terminate processeskill -KILL "$_cmd_pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/review-agent.sh:320 · Process kill command — agent can terminate processeskill "$_watch_pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/utils.sh:249 · Process kill command — agent can terminate processesif [[ -n "$lock_pid" ]] && ! kill -0 "$lock_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/review-agent.sh:311 · Process kill command — agent can terminate processesif kill -0 "$_cmd_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/stop-agent.sh:121 · Python subprocess execution detectedagent['cancelledAt'] = int(subprocess.run(['date', '+%s'], capture_output=True).stdout.strip()) * 1000Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/review-agent.sh:313 · Process kill command — agent can terminate processeskill -TERM "$_cmd_pid" >/dev/null 2>&1 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/stop-agent.sh:127 · Python subprocess execution detectedhas_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.
AST05
MEDIUM
Python subprocess execution detectedscripts/stop-agent.sh:118 · Python subprocess execution detectedresult = 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.
AST05
MEDIUM
Python subprocess execution detectedscripts/recommend-agent.sh:196 · Python subprocess execution detectedproc = 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.
AST05
MEDIUM
Python subprocess execution detectedscripts/recommend-agent.sh:184 · Python subprocess execution detectedsubprocess.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.
AST05

Cost to the agent

Instructions loaded
≈4,569 tok
2 files · 41 in bundle

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.