Skills/PyPI/db-conn-mcp

db-conn-mcp@0.7.1

BLOCKED

Publisher claims: "A dead-simple, self-hosted MCP server for securely querying databases via AI agents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher idle-sync · joined 3 days agoInstalls 371Last detonated 3d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-29 and scored it 48/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Privileged sudo command; Outbound HTTP to raw IP address; Privileged sudo command. 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
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/db-conn-mcp
0.1sprocessexited 127: timeout: failed to run command '.venv/bin/db-conn-mcp': No such file or directory
0.1sclaimedno tools/list reply (exit 127)
0.1sprocessscript backend runs setup only

Static findings

HIGH
Privileged sudo commandsrc/db_conn_mcp/dialects/postgres.py:601 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Outbound HTTP to raw IP addresssrc/db_conn_mcp/gui/app.py:750 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actionCLAUDE.md:56 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Privileged sudo commandsrc/db_conn_mcp/server.py:151 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/db_conn_mcp/server.py:150 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Rule modification attemptdocs/PRD.md:25 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentsrc/db_conn_mcp/gui/static/index.html:7 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsCLAUDE.md:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL using raw IP addresssrc/db_conn_mcp/cli.py:622 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addresssrc/db_conn_mcp/verify.py:175 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addresssrc/db_conn_mcp/cli.py:622 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresssrc/db_conn_mcp/gui/app.py:750 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandsrc/db_conn_mcp/gui/app.py:679 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
URL using raw IP addresssrc/db_conn_mcp/verify.py:175 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandsrc/db_conn_mcp/server.py:493 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/db_conn_mcp/server.py:250 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Hex-encoded string detectedtests/test_postgres.py:1063 · Hex-encoded string detected — may contain obfuscated payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedtests/test_doctor.py:159 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addresstests/test_gui_lifecycle.py:203 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedsrc/db_conn_mcp/verify.py:151 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/db_conn_mcp/gui/app.py:681 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Outbound HTTP to raw IP addresstests/test_gui_lifecycle.py:203 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresstests/test_gui_lifecycle.py:86 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandsrc/db_conn_mcp/doctor.py:312 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Outbound HTTP to raw IP addresstests/test_gui_lifecycle.py:86 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/test_doctor.py:147 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/db_conn_mcp/doctor.py:350 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/db_conn_mcp/doctor.py:336 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

What would make this Verified

32 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Asks the agent to act silently or skip confirmation≈ +8 on the totalRemove "do not tell the user", "without asking", "disable safety" and similar. An agent skill should never ask to be invisible.
  3. Unclaimed publisher≈ +8 on the totalClaim idle-sync: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
  6. Privileged sudo command≈ +4 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 idle-sync