Skills/PyPI/mcp-trilock

mcp-trilock@0.2.0

VERIFIED· not started

Publisher claims: "A drop-in MCP proxy that makes the lethal trifecta structurally impossible." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher poojan6216 · publishing for 72 daysInstalls 70Last detonated 4d ago
$claude mcp add mcp-trilock -- uvx mcp-trilock
WatchReport an issue

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 allowed.com, evil.com — 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 mcp-trilock

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 2026-11-10 and scored it 80/100 (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 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

MEDIUM
Python subprocess execution detectedbench/run_bench.py:56 · Python subprocess execution detectedreturn subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
False input termination markerdocs/demo.md:100 · False input termination marker — attempts to end user input section · informational: not an instruction file--- END MODEL-SUPPLIED ARGUMENTS ---Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/unit/test_scope.py:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("absolute escape", "/etc/passwd"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/trilock/policy/scope.py:189 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# pattern alone would let `/etc/passwd` satisfy `**` in a scopeFix: 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/unit/test_scope.py:36 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("home escape", "~/.ssh/id_rsa"),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/unit/test_scope.py:160 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert not check(ToolClass(effect=Effect.EXTERNAL), {"path": "/etc/passwd"}).violatedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Rule modification attemptBUILD_SPEC.md:290 · Rule modification attempt — overwriting existing instructions · informational: not an instruction fileHard Rule 4: same (call, session, policy) MUST yield the same Decision,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedbench/adaptive/attacker.py:307 · Python subprocess execution detected"commit": subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/trilock/policy/suggest.py:32 · Process kill command — agent can terminate processesdisable execute run exec start stop restart kill submit approve reject notify email messageFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injection attemptBUILD_SPEC.md:447 · Prompt injection attempt — model control tokens · informational: not an instruction file…ignals: imperative-to-system phrasing patterns, role-token strings (`system:`, `<|im_start|>`, `[INST]`, `###Instruction`), tool-name mentions inside content, URL-with-embe…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedbench/soak.py:38 · Python subprocess execution detectedCOMMIT = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/trilock/policy/scope.py:354 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# /etc/passwd, which costs utility and buys nothing: the argument thatFix: 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/unit/test_scope.py:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("nul byte", "./workspace/ok.txt\x00/../../etc/passwd"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionbench/soak.py:5 · File type combined with upload action — agent may exfiltrate local data filesWrites bench/results/soak.json with RSS sampled every second, call throughput,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
References a credential file in the home directorytests/unit/test_scope.py:36 · References a credential file in the home directory("home escape", "~/.ssh/id_rsa"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedbench/detector_latency.py:66 · Python subprocess execution detectedreturn subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL with embedded credentialstests/unit/test_scope.py:84 · URL with embedded credentials — may be phishing or credential leaking("userinfo with password", "https://api.allowed.com:[email protected]/x"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Access to sensitive file pathstests/unit/test_scope.py:89 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("file scheme", "file:///etc/passwd"),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
≈55 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 mcp-trilock@0.2.0 as of 4d ago. This is the package itself, not its dependencies.

mcp-trilock@0.2.0 safety verdict: Verified (not started) — KillerSkills