Is Adeu MCP server safe?
- Python shell/command execution
- Python filesystem read
- Python filesystem write/delete
adeu is an AI python_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 5 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 3.0.6
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 (5)
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 number, ln in enumerate(manifest_path.read_text(encoding="utf-8").splitlines(), 1):
digest = (manifest_path.parent / "INPUT_SHA256.txt").read_text(encoding="ascii").strip()
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()))
data = json.loads(cache_file.read_text(encoding="utf-8"))
existing_data = json.loads(cache_file.read_text(encoding="utf-8"))
data = Path(path).read_bytes()
with open(asset_path, "r", encoding="utf-8") as f:
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 / filename).write_text(text, 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 →