Skills/PyPI/minirag-mcp

minirag-mcp@1.0.0

CAUTION· not started

Publisher claims: "Local-first RAG MCP server: hybrid search over your documents, fully local" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 723 daysInstalls 347Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution 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 code
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx minirag-mcp

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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-11 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL to the cloud instance metadata address; References a credential file in the home directory; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

CRITICAL
URL to the cloud instance metadata addresssrc/minirag_mcp/ingest/parser.py:190 · URL to the cloud instance metadata address — reads the VM's credentialspermitted public host answering `302 -> http://169.254.169.254/` would have itsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
References a credential file in the home directorysrc/minirag_mcp/ingest/scanner.py:134 · References a credential file in the home directory`notes.md -> ~/.ssh/id_rsa` link would pull an arbitrary readable file into theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File permission modification commandtests/test_sync.py:789 · File permission modification command — agent changes file ownership/permissions@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a chmod 000 folder anyway")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedtests/test_cli.py:279 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedevals/behaviour/run.py:229 · Python subprocess execution detectedproc = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File permission modification commandtests/test_sync.py:805 · File permission modification command — agent changes file ownership/permissions@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a chmod 000 folder anyway")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
URL to the cloud instance metadata addresstests/test_pipeline.py:174 · URL to the cloud instance metadata address — reads the VM's credentialsp.ingest_url("http://169.254.169.254/latest/meta-data/")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedevals/behaviour/run.py:104 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Access to sensitive file pathstests/test_security.py:236 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescheck_url("http:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_security.py:52 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresolve_in_roots("/etc/passwd", [a, b])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandtests/test_cli.py:510 · File permission modification command — agent changes file ownership/permissions@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a chmod 000 folder anyway")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/test_server.py:172 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesawait c.call_tool("ingest_file", {"filePath": "/etc/passwd"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL to the cloud instance metadata addresstests/test_security.py:190 · URL to the cloud instance metadata address — reads the VM's credentialscheck_url("http://169.254.169.254/latest/meta-data/", allow_private=True)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File permission modification commandtests/test_sync.py:243 · File permission modification command — agent changes file ownership/permissions@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a chmod 000 folder anyway")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedevals/behaviour/run.py:137 · Python subprocess execution detectedproc = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
LOW
URL to a private-network addresstests/test_pipeline.py:206 · URL to a private-network address — a LAN or development targetassert res.source == "http://192.168.1.10/wiki"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathssrc/minirag_mcp/ingest/scanner.py:134 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`notes.md -> ~/.ssh/id_rsa` link would pull an arbitrary readable file into theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Privileged sudo commandtests/test_cli.py:221 · Privileged sudo command — agent may execute with elevated privilegesA root-owned `.sync.lock` left by one `sudo minirag-mcp sync` is the realisticFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
URL to a private-network addresstests/test_pipeline.py:205 · URL to a private-network address — a LAN or development targetres = Pipeline(store, fake_embedder, cfg).ingest_url("http://192.168.1.10/wiki")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandtests/test_cli.py:222 · File permission modification command — agent changes file ownership/permissionsshape of this; chmod 000 reproduces it without sudo. Before the lock existedFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandtests/test_lock.py:326 · File permission modification command — agent changes file ownership/permissionspytest.skip("running as root: chmod denies nothing")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/test_security.py:112 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"file:///etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_security.py:42 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresolve_in_roots("/etc/passwd", [other])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandtests/test_cli.py:254 · File permission modification command — agent changes file ownership/permissionspytest.skip("running as root: chmod 000 denies nothing")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandtests/test_parity.py:166 · File permission modification command — agent changes file ownership/permissions@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a chmod 000 folder anyway")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/test_pipeline.py:166 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesp.ingest_url("file:///etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_server.py:192 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesawait c.call_tool("ingest_url", {"url": "file:///etc/passwd"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandtests/test_sync.py:593 · File permission modification command — agent changes file ownership/permissions@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a chmod 000 folder anyway")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandtests/test_lock.py:147 · Process kill command — agent can terminate processeswith pytest.raises(SyncLockBusy): # genuinely held before the killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandtests/test_sync.py:187 · File permission modification command — agent changes file ownership/permissions@pytest.mark.skipif(os.geteuid() == 0, reason="root reads a chmod 000 folder anyway")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/test_security.py:195 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescheck_url("file:///etc/passwd", allow_private=True)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈3,042 tok
3 files · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for minirag-mcp@1.0.0 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. URL to the cloud instance metadata address≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim pypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pypiPropose a patch to the maintainer