Book a 30-minute demo →

Skill scan report

wtt-skill

View on GitHub

100 Critical This skill sends sensitive values to an external host and reads local credential files. Automated analysis flagged 7 additional risk patterns.

What this skill does

WTT (Want To Talk) agent messaging and orchestration skill for OpenClaw with topic/P2P communication, task and pipeline operations, delegation, IM routing, and WebSocket-first autopoll runtime.

github/leoyeai - Data Flow - 2.1k stars

ThreatsData Flow Privilege Escalation Tool Misuse Code Execution Data Exfiltration Dangerous Code Execution

Threat analysis

Data Flow2 findings

Privilege Escalation5 findings

Tool Misuse3 findings

Code Execution1 finding

Data Exfiltration1 finding

Dangerous Code Execution1 finding

Skill info

Nameleoyeai/wtt-skill

Registrygithub

Versione5199b5

PURLpkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=wtt-skill

Stars2.1k

SourceView on GitHub

This skill was flagged with critical risk. Review the findings below before installing.

Assessments (13)

Data Flow2 findings CRITICAL

CRITICAL

Data Flow via skillspector

handler.py

                    resp = httpx.post(f"{api_url}/agents/register", json={"platform": "openclaw"}, timeout=15)

CRITICAL

Data Flow via skillspector

start_wtt_autopoll.py

        resp = httpx.post(f"{api_url}/agents/register", json={"platform": "openclaw"}, timeout=15)

Privilege Escalation5 findings HIGH

HIGH

Privilege Escalation via skillspector

README.md

.env

HIGH

Privilege Escalation via skillspector

SKILL.md

.env

HIGH

Privilege Escalation via skillspector

handler.py

.env

HIGH

Privilege Escalation via skillspector

scripts/install_autopoll.sh

.env"

HIGH

Privilege Escalation via skillspector

start_wtt_autopoll.py

.env

Tool Misuse3 findings HIGH

HIGH

Tool Misuse via skillspector

scripts/install_autopoll.sh

rm -rf "$SKILL_ROOT/.venv"

HIGH

Tool Misuse via skillspector

scripts/install_autopoll.sh

&& rm -

HIGH

Tool Misuse via skillspector

scripts/uninstall_autopoll.sh

rm -f "$HOME/.config/systemd/user/wtt-autopoll.service"

Code Execution1 finding HIGH

HIGH

Code Execution via local-llm-review

__init__.py

The script uses `subprocess.run` with `bash` to execute arbitrary scripts, which could be exploited to run malicious code if the script path is not properly validated.

Data Exfiltration1 finding HIGH

HIGH

Data Exfiltration via skillspector

start_wtt_autopoll.py

extract conversation

Dangerous Code Execution1 finding MEDIUM

MEDIUM

Dangerous Code Execution via skillspector

__init__.py

        subprocess.run(
            ["bash", str(script)],
            stdout=subprocess.DEVNULL,
            stderr=subprocess.DEVNULL,
            timeout=180,
            check=False,
        )

Badge

Add the Anomity scan badge for wtt-skill to your README.

Markdown

[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/leoyeai/wtt-skill/)

HTML

<a href="https://anomity.ai/skills/github/leoyeai/wtt-skill/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>

Image URL

https://anomity.ai/skills/badge.svg

How Anomity governs this at runtime

Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.

Book a 30-minute demo to see your own skill inventory.

Methodology and disputes

Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of wtt-skill? Report an issue or request a rescan.

Ask AI about Anomity