Is Adeu MCP server safe?
- Python shell/command execution
- Node.js shell/command execution
- Python filesystem read
adeu is an AI python_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 6 risky constructs are reported for review. It can: filesystem read, filesystem write, mcp tools detected, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
adeu 2.4.0
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Adeu MCP server's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (6)
The component can run operating-system commands or spawn processes.
`)}var S=class{options;rules;lexer;constructor(e){this.options=e||w}space(e){let t=this.rules.block.newline.exec(e);if(t&&t[0].length>0)return{type:"space",raw:t[0]}}code(e){let t=this.rules.block.code.exec(e);if(t){let n=t[0].replace(this. …`)}}}fences(e){let t=this.rules.block.fences.exec(e);if(t){let n=t[0],s=rt(n,t[3]||"",this.rules);return{type:"code",raw:n,lang:t[2]?t[2].trim().replace(this.rules.inline.anyPunctuation,"$1"):t[2],text:s}}}heading(e){let t=this.rules.block. …`)}}blockquote(e){let t=this.rules.block.blockquote.exec(e);if(t){let n=A(t[0],``);continue}}return{type:"blockquote",raw:s,tokens:r,text:i}}}list(e){let t=this.rules.block.list.exec(e);if(t){let n=t[1].trim(),s=n.length>1,i={type:"list",raw:"",ordered:s,start:s?+n.slice(0,-1):"",loose:!1,items:[]};n=s?`\\d{1,9}\\${n.s …`,e=e.substring(G.length+1),d=C.slice(f)}}i.loose||(o?i.loose=!0:this.rules.other.doubleBlankLine.test(p)&&(o=!0));let y=null,ee;this.options.gfm&&(y=this.rules.other.listIsTask.exec(u),y&&(ee=y[0]!=="[ ] ",u=u.replace(this.rules.other.list …
`):[],r={type:"table",raw:t[0],header:[],align:[],rows:[]};if(n.length===s.length){for(let o of s)this.rules.other.tableAlignRight.test(o)?r.align.push("right"):this.rules.other.tableAlignCenter.test(o)?r.align.push("center"):this.rules.oth …`?t[1].slice(0,-1):t[1];return{type:"paragraph",raw:t[0],text:n,tokens:this.lexer.inline(n)}}}text(e){let t=this.rules.block.text.exec(e);if(t)return{type:"text",raw:t[0],text:t[0],tokens:this.lexer.inline(t[0])}}escape(e){let t=this.rules. …`+s.text,this.inlineQueue.pop(),this.inlineQueue.at(-1).src=r.text):t.push(s);continue}if(e){let r="Infinite loop on byte: "+e.charCodeAt(0);if(this.options.silent){console.error(r);break}else throw new Error(r)}}return this.state.top=!0,t} …Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.
The component can run operating-system commands or spawn processes.
proc = subprocess.Popen(
["uv", "run", "adeu-server"],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.DEVNULL, # Ignore server logs
text=True,
)git_sha = subprocess.check_output(
["git", "rev-parse", "--short", "HEAD"],
cwd=str(Path(__file__).parent),
stderr=subprocess.DEVNULL,
text=True,
).strip()build_ts_raw = subprocess.check_output(
["git", "log", "-1", "--format=%ct"],
cwd=str(Path(__file__).parent),
stderr=subprocess.DEVNULL,
text=True,
).strip()subprocess.run(["open", str(p)], check=True)
subprocess.run(["xdg-open", str(p)], check=True)
Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; avoid shell=True.
The component reads files from disk.
with open(test_json_path, "r", encoding="utf-8") as f:
with open(input_docx_path, "rb") as f:
return path.read_bytes()
for ln in manifest_path.read_text(encoding="utf-8").splitlines():
b = (base / "MANIFEST.txt").read_text(encoding="utf-8").splitlines()
n = (new / "MANIFEST.txt").read_text(encoding="utf-8").splitlines()
bt = (base / k).read_text(encoding="utf-8")
nt = (new / k).read_text(encoding="utf-8")
with open(path, "r", encoding="utf-8") as f:
with open(path, "r", encoding="utf-8") as f:
with open(input_path, "rb") as f:
with open(path, "r", encoding="utf-8") as f:
with open(path, "r", encoding="utf-8") as f:
with open(config_path, "r", encoding="utf-8") as f:
and 'name = "adeu"' in (cwd / "pyproject.toml").read_text(encoding="utf-8", errors="ignore")
current_content = config_path.read_text(encoding="utf-8")
raw = path.read_bytes()
with open(path, "rb") as _fh:
with open(path, "rb") as f:
with open(path, "rb") as f:
diff_warnings.extend(collect_media_difference_warnings(args.original.read_bytes(), args.modified.read_bytes()))
text_data = cache_file.read_text(encoding="utf-8")
existing_raw = cache_file.read_text(encoding="utf-8")
data = Path(path).read_bytes()
with open(asset_path, "r", encoding="utf-8") as f:
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component writes or deletes files on disk.
(test_dir / "golden_raw.md").write_text(raw_md, encoding="utf-8")
(test_dir / "golden_clean.md").write_text(clean_md, encoding="utf-8")
(test_dir / "golden_abstract.xml").write_text(abstract_xml, encoding="utf-8")
os.unlink(tmp_path)
(test_dir / "golden_raw.md").write_text(raw_md.replace("\r\n", "\n"), encoding="utf-8")(test_dir / "golden_clean.md").write_text(clean_md.replace("\r\n", "\n"), encoding="utf-8")(outdir / f"{name}.{view}.txt").write_text(text, encoding="utf-8", newline="")(outdir / "MANIFEST.txt").write_text("\n".join(manifest) + "\n", encoding="utf-8", newline="")with open(path, "w", encoding="utf-8") as f:
with open(output_path, "wb") as f:
with open(path, "w", encoding="utf-8") as f:
shutil.copy2(config_path, backup_path)
with open(config_path, "w", encoding="utf-8") as f:
tmp_file.write_text(content, encoding="utf-8")
with open(p, "wb") as f:
with open(fd, "w", encoding="utf-8") as f:
with open(dbg_path, "wb") as f:
Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
The component makes outbound network requests.
import urllib.request
req = urllib.request.Request(
url,
headers={
"Authorization": f"Bearer {api_key}",
"Accept": "application/json",
},
method="GET",
)with urllib.request.urlopen(req, timeout=10) as response:
Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.
Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.
An MCP tool surface (manifest or tool definitions) was found.
mcp = FastMCP(
Why it matters: Just context — review which tools it offers and their permissions.
Fix: Review the declared MCP tools and their permissions.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →