Skills/PyPI/iflow-mcp-rubenszimbres-a2a-adk-mcp

iflow-mcp-rubenszimbres-a2a-adk-mcp@0.1.0

CAUTION

Publisher claims: "A security-focused MCP server with SQL query capabilities and A2A protocol integration" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher iflow-mcp · joined 8 days agoInstalls 15Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-04 and scored it 51/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive command against a filesystem root or device; Privileged sudo command; 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
0.2sprocessdependency install exit 1
0.3sprocessexec /usr/bin/timeout
0.3sprocessexec .venv/bin/a2a-mcp-server
0.3sprocessexited 127: timeout: failed to run command '.venv/bin/a2a-mcp-server': No such file or directory
0.3sclaimedno tools/list reply (exit 127)
0.3sprocessscript backend runs setup only

Static findings

CRITICAL
Destructive command against a filesystem root or deviceclients/query_MCP_ADK_A2A.py:790 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandclients/query_MCP_ADK_A2A.py:414 · 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 commandevaluation/security_test_results.json:42 · Privileged sudo command — agent may execute with elevated privilegesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Destructive file system command detectedevaluation/security_test_results.json:234 · Destructive file system command detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
Destructive command against a filesystem root or deviceevaluation/test_scenarios.json:25 · Destructive command against a filesystem root or deviceFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
document.cookie accessevaluation/security_test_results.json:362 · document.cookie access — can steal session cookiesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
CRITICAL
Destructive command against a filesystem root or deviceevaluation/security_test_results.json:42 · Destructive command against a filesystem root or deviceFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Destructive file system command detectedclients/query_MCP_ADK_A2A.py:790 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsevaluation/security_test_results.json:338 · 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
CRITICAL
Prompt injectionevaluation/security_test_results.json:138 · Prompt injection — explicit attempt to bypass safety measuresFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Destructive file system command detectedevaluation/security_test_results.json:42 · Destructive file system command detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
Prompt injection attemptevaluation/security_test_results.json:34 · Prompt injection attempt — 'ignore previous instructions'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Privileged sudo commandclients/query_MCP_ADK_A2A.py:790 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or deviceevaluation/security_test_results.json:234 · Destructive command against a filesystem root or deviceFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
Prompt injection attemptevaluation/test_scenarios.json:20 · Prompt injection attempt — 'ignore previous instructions'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
CRITICAL
Destructive command against a filesystem root or deviceevaluation/test_scenarios.json:145 · Destructive command against a filesystem root or deviceFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
Prompt injectionevaluation/test_scenarios.json:85 · Prompt injection — explicit attempt to bypass safety measuresFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Access to sensitive file pathsevaluation/security_test_results.json:186 · 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
HIGH
Access to sensitive file pathsevaluation/test_scenarios.json:115 · 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
HIGH
Destructive file system command detectedevaluation/test_scenarios.json:25 · Destructive file system command detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Access to sensitive file pathsevaluation/security_test_results.json:346 · 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
HIGH
Role reassignment attemptevaluation/security_test_results.json:34 · Role reassignment attemptFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Destructive file system command detectedevaluation/test_scenarios.json:145 · Destructive file system command detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
document.cookie accessevaluation/test_scenarios.json:230 · document.cookie access — can steal session cookiesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Privileged sudo commandevaluation/test_scenarios.json:25 · Privileged sudo command — agent may execute with elevated privilegesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Role reassignment attemptevaluation/test_scenarios.json:20 · Role reassignment attemptFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
Dense URL-encoded contentclients/query_MCP_ADK_A2A.py:542 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Dense URL-encoded contentclients/query_MCP_ADK_A2A.py:544 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsevaluation/test_scenarios.json:210 · 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
Dense URL-encoded contentclients/query_MCP_ADK_A2A.py:543 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Dense URL-encoded contentevaluation/test_scenarios.json:10 · Dense URL-encoded content — may be obfuscating payloadsFix: 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 commandclients/query_MCP_ADK_A2A.py:446 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Dense URL-encoded contentclients/query_MCP_ADK_A2A.py:535 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Dense URL-encoded contentevaluation/security_test_results.json:18 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsevaluation/test_scenarios.json:215 · 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
Dense URL-encoded contentclients/query_MCP_ADK_A2A.py:517 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

What would make this Verified

29 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. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Unclaimed publisher≈ +8 on the totalClaim iflow-mcp: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Destructive file system command 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.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim iflow-mcp