MCP server · Audited from source
New Term Radar MCP server
by zhuyansen/new-term-radarMIT licenceAudited 12 Nov 2026 · source 3be40a13958f
Is it safe? No — BLOCK, grade D (69/100). It exposes 3 tools: 2 read, 1 write and 0 destructive. The audit recorded 6 findings (0 critical, 2 high, 0 medium, 4 low). Maintainer's description: Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
Cite
Cite this page
ModelsAtlas. “New Term Radar MCP server (zhuyansen/new-term-radar)”. Retrieved 12 Nov 2026. https://modelsatlas.com/mcp/zhuyansen/new-term-radar
Why this is BLOCK. The audit found 0 critical and 2 high findings; the most severe is Prompt injection at skills/new-term-radar/SKILL.md:16. Each finding is listed below with its file and line.
Why this page is still public. People search for this server by name. Hiding it would leave them with the README's word alone; here they see what the code does. We list it so you can decide, and we do not show connect commands for BLOCK servers.
Trust audit
Audit 0.4.1 · full source read 12 Nov 2026
6 findings, listed below with the file and line each was found on. Grade A needs a sandboxed behavioural run too; this audit read the source only.
What the source does
- FilesystemNone observedNothing seen in the source
- NetworkDeclared5 observations
- ShellNone observedNothing seen in the source
- DependenciesNot pinnedSome ranges float
- SecretsNone foundNo keys in source
Findings (6)
Sorted by severity
HIGHPrompt injectionprompt.hide_from_user · skills/new-term-radar/SKILL.md:16
5. `GOANYAPI_API_KEY` is optional (a key comes from https://goanyapi.com/r/ga-95708898fb). With it the table also holds what people really searched together with each name, and reads the bigger rows f
- Why
- asks the agent to act without the user's knowledge
- Fix
- —
HIGHPrompt injectionprompt.hide_from_user · skills/seo-new-keywords-research/SKILL.md:17
4. `GOANYAPI_API_KEY` is optional (a key comes from https://goanyapi.com/r/ga-95708898fb). With it the table also holds what people really searched together with each name, and reads the bigger rows f
- Why
- asks the agent to act without the user's knowledge
- Fix
- —
LOWObfuscation / stealthobf.base64_blob · README.md:405
trae-cn://trae.ai-ide/mcp-import?type=stdio&name=new-term-radar&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLXdpdGgiLCJtY3AiLCJuZXctdGVybS1yYWRhciIsIm1jcCJdLCJlbnYiOnsiQUlTQV9BUElfS0VZIjoiIiwiR09BTllBU
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWObfuscation / stealthobf.base64_blob · README.zh-CN.md:400
trae-cn://trae.ai-ide/mcp-import?type=stdio&name=new-term-radar&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLXdpdGgiLCJtY3AiLCJuZXctdGVybS1yYWRhciIsIm1jcCJdLCJlbnYiOnsiQUlTQV9BUElfS0VZIjoiIiwiR09BTllBU
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWObfuscation / stealthobf.decode_call · radar/usecases.py:123
return base64.b64decode(json.load(res)["content"]).decode("utf-8", "replace")[:README_CHARS]- Why
- No further detail recorded for this rule.
- Fix
- —
LOWSupply chainsupply.unpinned · requirements.txt
markdown
- Why
- 1 requirement(s) not pinned with ==
- Fix
- pin exact versions
Tools it exposes
3 declared in source · 0 destructive
| Tool | What it does | Risk |
|---|---|---|
run_radar | Run the radar once and return its report. command: | write |
keyword_table | The keyword table for new names (models, products, repositories), read now: each name and | read |
recent_leads | Leads the radar kept in the last `days` days (newest first), each with its signals, name | read |
Safer alternatives
263311487-ux/dsh-verify
Browser acceptance checks for agent-built web apps. Zero-key starter, CLI, MCP and GitHub Action; inspect explicit assertions and reports.
markifact/markifact-mcp
MCP server for Google Ads, Meta Ads, GA4, TikTok Ads, and LinkedIn Ads. Manage 300+ ad operations from Claude, ChatGPT, Gemini, Cursor, or any AI client. Human-in-the-loop on every write.
AgentGameLab/mneme
Persistent long-term memory for Claude Code agents — SQLite + FTS5 + sqlite-vec + RRF hybrid recall over MCP, with Chinese tokenization. Local-first, graceful degradation.
Audit history
- ✕BLOCK D 69 / 100
First audit ·
3be40a13958f
README badge
Badges show the current verdict, BLOCK included
A badge cannot be hidden by the maintainer while the verdict is BLOCK. Fix the findings, push, and the re-audit updates it.
Questions about New Term Radar MCP server
What is the New Term Radar MCP server?
What tools does New Term Radar expose?
Is New Term Radar safe to connect to an agent?
What credentials does New Term Radar need?
How does New Term Radar run?
How current is this page?
I already installed New Term Radar. What should I do?
Can the verdict change?
Sources
- zhuyansen/new-term-radar on GitHub — the source we read, its licence, stars and activityObserved · 12 Nov 2026
- ModelsAtlas trust audit — BLOCK verdict for commit 3be40a13958fObserved · 12 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What is the New Term Radar MCP server?
- What tools does New Term Radar expose?
- Is New Term Radar safe to connect to an agent?