Skills/PyPI/qwed-mcp

qwed-mcp@0.3.0

CAUTION· not started

Publisher claims: "MCP Server for QWED Verification - Use QWED verification tools in Claude Desktop, VS Code, and any MCP client" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher qwed-ai · publishing for 2 daysInstalls 436Last detonated 28 min 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
SENTRY_DSNConfiguration, not credentials: PYTHONPATH, QWED_MCP_BACKGROUND_TIMEOUT, QWED_MCP_TRUSTED_CODE_EXECUTION, QWED_SKILL_MANIFEST
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 with a scoped credential, under the guard. It asks for SENTRY_DSN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx qwed-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 2026-11-15 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hex-encoded string detected; Collapsed <details> block carrying instructions. 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
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandsrc/qwed_mcp/tools.py:150 · Process kill command — agent can terminate processes# Setup process group definition for Unix to cleanly kill child processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_code_admission.py:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"rebind_open": 'o = open\no("/etc/passwd").read()',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hex-encoded string detectedsrc/qwed_mcp/engines/sql_engine.py:140 · Hex-encoded string detected — may contain obfuscated payloads_LINE_BREAKS = frozenset("\r\x0b\x0c\x1c\x1d\x1e\x85\u2028\u2029")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Process kill commandtests/test_process_cleanup.py:1 · Process kill command — agent can terminate processes"""Process cleanup in tools.py: a failed kill or wait is logged, notFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_code_admission.py:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"builtins_open": 'import builtins\nbuiltins.open("/etc/passwd").read()',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:250 · Collapsed <details> block carrying instructions<summary><b>Do I need an API key?</b></summary> No. QWED-MCP runs entirely locally. No API keys, no cloud calls.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
OS command execution function call detectedtests/test_provenance_guard.py:446 · OS command execution function call detected"source_url": "https://github.com/e/x?cmd=os.system('id')",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_sql_engine.py:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"load_file": "SELECT load_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_code_admission.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"pathlib_read": 'import pathlib\npathlib.Path("/etc/passwd").read_bytes()',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/qwed_mcp/tools.py:48 · Process kill command — agent can terminate processeslogger.debug(f"Failed to kill process group: {e}, falling back to proc.kill()")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈62 tok
1 file · 41 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim qwed-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Hex-encoded string detected≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. 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.
  6. OS command execution function call detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim qwed-aiPropose a patch to the maintainer