Skills/ClawHub/ai-mother

ai-mother@1.0.1

VERIFIED· install only

Publisher claims: "AI Mother - Monitor and manage other AI agents (Claude Code, Codex, Gemini, etc.). Use when asked to check AI execution status, supervise AI agents, help stu..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher guguoyi · publishing for 243 daysInstalls 1,202Last detonated 25 min ago
$clawhub install ai-mother
WatchReport an issue

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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; install scripts ran; no agent task scenario for this bundle) on 2026-11-16 and scored it 81/100 (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 · 180 s · 2 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
60sprocessexceeded 60s
60sprocessscript backend runs setup only
60sprocessscript backend runs setup only
120sprocesssecond launch, clock +45 days, CI unset
180sprocessexceeded 60s on second launch

Static findings

MEDIUM
Python subprocess execution detectedscripts/dashboard.py:32 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/cleanup-duplicates.sh:108 · Process kill command — agent can terminate processeskill -9 "$PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedscripts/dashboard.py:156 · Hidden zero-width characters detected — may conceal contentconsole.print("[bold cyan]👩‍👧‍👦 AI Mother Dashboard[/bold cyan]")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandscripts/resume-ai.sh:33 · Process kill command — agent can terminate processeskill -CONT "$PID"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedSKILL.md:6 · Hidden zero-width characters detected — may conceal contentemoji: 👩‍👧‍👦Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detectedscripts/dashboard.py:99 · Hidden zero-width characters detected — may conceal content"[bold cyan]👩‍👧‍👦 AI Mother Dashboard[/bold cyan]\n"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandscripts/cleanup-duplicates.sh:104 · Process kill command — agent can terminate processeskill "$PID" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:241 · Process kill command — agent can terminate processes⚠️ **Use judgment:** answer AI permission requests, provide config values, kill processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedscripts/format-notification.sh:39 · Hidden zero-width characters detected — may conceal contentecho "👩‍👧‍👦 AI Mother Patrol Report"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detectedSKILL.md:61 · Hidden zero-width characters detected — may conceal contentconsole.print("\n[bold cyan]👩‍👧‍👦 AI Mother Dashboard[/bold cyan]")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandscripts/auto-heal.sh:197 · Process kill command — agent can terminate processesecho " Suggestion: User can safely kill this process"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedscripts/setup.sh:8 · Hidden zero-width characters detected — may conceal contentecho "👩‍👧‍👦 AI Mother Setup Wizard"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandscripts/cleanup-duplicates.sh:117 · Process kill command — agent can terminate processesecho " To kill a specific PID: kill <PID>"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/detect-stuck.sh:66 · Process kill command — agent can terminate processesecho " 2. Send Ctrl+C: kill -INT $PID"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/cleanup-duplicates.sh:118 · Process kill command — agent can terminate processesecho " To kill all but one: kill ${PIDS[@]:1}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedscripts/setup.sh:88 · Hidden zero-width characters detected — may conceal contentTEST_MSG="👩‍👧‍👦 AI Mother setup complete! I'll notify you when AI agents need attention."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Process kill commandscripts/detect-stuck.sh:67 · Process kill command — agent can terminate processesecho " 3. If frozen: kill -9 $PID (last resort)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,747 tok
1 file · 39 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.

ai-mother@1.0.1 safety verdict: Verified (install only) — KillerSkills