wb-agent-runtime-mcp@1.0.1
VERIFIED· install onlyPublisher claims: "智能体本地运行时:长期记忆与知识图谱 + DAG 任务流水线编排,零密钥零依赖" 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
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 8 of 37 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
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso huggingface.co, githubusercontent.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it under the guard. Bundled scripts ran with no arguments; no agent task scenario for this bundle. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 82/100 (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 · 3 scenariosStatic findings
report <state.json> [output] ★★☆ 生成 Markdown 执行报告(visualize --format md 别名)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proc = subprocess.run(f'schtasks /query /tn "{TASK_NAME}"',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.python pipeline_reporter.py report <state.json> [output.md] (向后兼容)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.print(" python pipeline_reporter.py visualize <state.json> [--format md|html|both] [output]")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.python pipeline_reporter.py gantt <state.json> [output.html] (向后兼容)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.print(" python pipeline_reporter.py report <state.json> [output.md] (向后兼容)")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proc = subprocess.run(["crontab", "-"], input=new_cron,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.print("用法:python orchestrator.py gantt <state.json> [output.html]")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.python pipeline_reporter.py visualize <state.json> [--format md|html|both] [output]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proc = subprocess.run(schtasks, shell=True, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.gantt <state.json> [output.html] ★★☆ 生成 HTML 甘特图(visualize --format html 别名)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.cur = subprocess.run(["crontab", "-l"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.visualize <state.json> [--format md|html|both] [output] ★★★ 统一可视化(MD+HTML)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.print("用法:python orchestrator.py report <state.json> [output.md]")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.cur = subprocess.run(["crontab", "-l"], 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(["crontab", "-"], input=new_cron,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(f'schtasks /delete /tn "{TASK_NAME}" /f',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.cur = subprocess.run(["crontab", "-l"], 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.runpy.run_path(os.path.join(here, "scripts", "mcp_server.py"), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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
No advisories in OSV for wb-agent-runtime-mcp@1.0.1 as of 32 min ago. This is the package itself, not its dependencies.