memscope-mcp@0.4.0
VERIFIED· not startedPublisher claims: "AI-native memory research MCP server for reverse engineering" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher boti-ormandi · publishing for 181 daysInstalls 52Last detonated 3d ago
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: Verified 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 codeAlso esrc.dev — not the publisher's domain; check what for before connecting.
- 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 memscope-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 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationst+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
MEDIUM
Hex-encoded string detectedtests/test_disasm.py:40 · Hex-encoded string detected — may contain obfuscated payloads
AST07assert instruction_length(b"\x48\x81\xec\x00\x01\x00\x00") == 7Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_disasm.py:44 · Hex-encoded string detected — may contain obfuscated payloads
AST07data = b"\x48\xb8" + b"\x01\x02\x03\x04\x05\x06\x07\x08"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Python subprocess execution detectedbenchmarks/scanning/run.py:385 · Python subprocess execution detected
AST05process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedbenchmarks/scanning/run.py:188 · Python subprocess execution detected
AST05completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Hex-encoded string detectedtests/test_disasm.py:106 · Hex-encoded string detected — may contain obfuscated payloads
AST07instruction_length(b"\x48\x8b\x05\x10\x20\x30\x40")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Python subprocess execution detectedbenchmarks/scanning/run.py:940 · Python subprocess execution detected
AST05subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedbenchmarks/scanning/run.py:1005 · Python subprocess execution detected
AST05subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Hex-encoded string detectedtests/test_deref_args.py:22 · Hex-encoded string detected — may contain obfuscated payloads
AST07STATUS_COMPLETE = b"\x41\xc7\x45\x08\x02\x00\x00\x00" # mov dword [r13+0x08], STATUS_COMPLETEFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Python subprocess execution detectedbenchmarks/scanning/run.py:316 · Python subprocess execution detected
AST05completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Hex-encoded string detectedtests/test_disasm.py:126 · Hex-encoded string detected — may contain obfuscated payloads
AST07data = b"\xf0\x49\x0f\xb1\x14\x24"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
npx invocation of non-well-known package.github/workflows/site.yml:47 · npx invocation of non-well-known package — may execute untrusted code
AST06run: npx playwright testFix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
npx invocation of non-well-known package.github/workflows/site.yml:43 · npx invocation of non-well-known package — may execute untrusted code
AST06run: npx playwright install --with-deps chromiumFix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
Hex-encoded string detectedtests/test_heuristics.py:34 · Hex-encoded string detected — may contain obfuscated payloads
AST07assert _is_printable("a\x01\x02\x03\x04\x05\x06\x07\x08\x09") is FalseFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_disasm.py:101 · Hex-encoded string detected — may contain obfuscated payloads
AST07instruction_length(b"\x48\x8d\x05\x10\x20\x30\x40")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_shellcode.py:129 · Hex-encoded string detected — may contain obfuscated payloads
AST07assert b"\x66\x48\x0f\x7e\x43\x08" not in codeFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_shellcode.py:124 · Hex-encoded string detected — may contain obfuscated payloads
AST07assert b"\x66\x48\x0f\x7e\x43\x08" in codeFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/site-routes.md:15 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST01| `/guides/read-and-write-memory/` | [`site/src/content/docs/guides/read-and-write-memory.md`](../site/src/content/docs/guides/read-and-write-memory.md) |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.MEDIUM
Hex-encoded string detectedtests/test_lua_network.py:82 · Hex-encoded string detected — may contain obfuscated payloads
AST07peer_data = b"\x02\x00\x01\xbb\xcb\x00\x71\x09" + b"\x00" * 20Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_lua_network.py:83 · Hex-encoded string detected — may contain obfuscated payloads
AST07local_data = b"\x02\x00\xc9\x3b\x0a\x00\x00\x05" + b"\x00" * 20Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_relocation.py:68 · Hex-encoded string detected — may contain obfuscated payloads
AST07info = decode_instruction(b"\xc7\x05\x00\x10\x00\x00\x42\x00\x00\x00")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_relocation.py:44 · Hex-encoded string detected — may contain obfuscated payloads
AST07info = decode_instruction(b"\x48\x8d\x05\x00\x10\x00\x00")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_heuristics.py:81 · Hex-encoded string detected — may contain obfuscated payloads
AST07assert _looks_like_inline_string(b"\x01\x02\x03\x04\x05\x06\x07\x08") is FalseFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_heuristics.py:145 · Hex-encoded string detected — may contain obfuscated payloads
AST07data = b"\x01\x80\x01\x80\x01\x80\x01\x80"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_relocation.py:60 · Hex-encoded string detected — may contain obfuscated payloads
AST07info = decode_instruction(b"\x48\x3b\x05\x78\x56\x00\x00")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_relocation.py:108 · Hex-encoded string detected — may contain obfuscated payloads
AST07info = decode_instruction(b"\x0f\x84\x00\x10\x00\x00")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_relocation.py:52 · Hex-encoded string detected — may contain obfuscated payloads
AST07info = decode_instruction(b"\x48\x8b\x0d\x00\x20\x00\x00")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.MEDIUM
Hex-encoded string detectedtests/test_heuristics.py:89 · Hex-encoded string detected — may contain obfuscated payloads
AST07assert _looks_like_inline_string(b"A\x01\x02\x03\x04\x05\x06\x07") is FalseFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Cost to the agent
Instructions loaded
≈51 tok
1 file · 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 memscope-mcp@0.4.0 as of 3d ago. This is the package itself, not its dependencies.