Skills/PyPI/honeymcp

honeymcp@0.1.8

CAUTION

Publisher claims: "Deception middleware for AI agents - detecting data theft and indirect prompt injection in MCP servers" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher barvhaim · joined 2 days agoInstalls 48Last detonated 39 h ago

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-01 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Outbound HTTP to raw IP address; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.4sprocessdependency install exit 1
0.4sprocessexec /usr/bin/timeout
0.4sprocessexec .venv/bin/honeymcp
0.4sprocessexited 127: timeout: failed to run command '.venv/bin/honeymcp': No such file or directory
0.4sclaimedno tools/list reply (exit 127)
0.4sprocessscript backend runs setup only

Static findings

HIGH
Outbound HTTP to raw IP addressAGENTS.md:15 · 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
Access to sensitive file pathsAGENTS.md:38 · 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 pathsCLAUDE.md:46 · 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 pathsCLAUDE.md:152 · 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 pathsCLAUDE.md:59 · 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 pathssrc/honeymcp/cli.py:57 · 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 pathsCLAUDE.md:172 · 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
Outbound HTTP to raw IP addressCLAUDE.md:35 · 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 addressscripts/_demo_attack.py:28 · 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
Access to sensitive file pathssrc/honeymcp/cli.py:51 · 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 pathsscripts/_demo_attack.py:22 · 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 pathssrc/honeymcp/cli.py:142 · 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
Credential pass-through configurationsrc/honeymcp/core/ghost_tools.py:49 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/honeymcp/core/ghost_tools.py:73 · 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
Credential pass-through configurationsrc/honeymcp/core/ghost_tools.py:63 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/honeymcp/core/ghost_tools.py:722 · 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 pathssrc/honeymcp/cli.py:112 · 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
Stripe-like API key pattern detectedsrc/honeymcp/core/ghost_tools.py:76 · Stripe-like API key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Credential pass-through configurationsrc/honeymcp/core/tool_creator.py:312 · Credential pass-through configuration — agent relays sensitive credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Outbound HTTP to raw IP addresssrc/honeymcp/dashboard/react_umd/app.js:187 · 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
Stripe-like API key pattern detectedsrc/honeymcp/core/ghost_tools.py:41 · Stripe-like API key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Outbound HTTP to raw IP addresssrc/honeymcp/dashboard/arsenal_chat/app.js:127 · 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
Access to sensitive file pathssrc/honeymcp/core/ghost_tools.py:71 · 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
AWS access key pattern detectedsrc/honeymcp/core/ghost_tools.py:83 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Access to sensitive file pathssrc/honeymcp/cli.py:192 · 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 addressAGENTS.md:15 · 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
URL using raw IP addresssrc/honeymcp/dashboard/react_umd/app.js:187 · 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
Slack webhook URLtests/test_alerting.py:424 · Slack webhook URL — data will be sent to SlackFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/honeymcp/llm/clients/__init__.py:9 · 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
Slack webhook URLtests/test_alerting.py:300 · Slack webhook URL — data will be sent to SlackFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
URL with embedded credentialssrc/honeymcp/dashboard/react_umd/index.html:15 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/honeymcp/llm/clients/__init__.py:11 · 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 addressscripts/_demo_attack.py:28 · 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
URL using raw IP addresssrc/honeymcp/dashboard/arsenal_chat/app.js:127 · 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
Outbound HTTP to raw IP addressMakefile:43 · 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 with suspicious TLDsrc/honeymcp/cli.py:91 · URL with suspicious TLD — commonly used for phishing/malwareFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addressCLAUDE.md:35 · 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
Slack webhook URLtests/test_alerting.py:472 · Slack webhook URL — data will be sent to SlackFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/honeymcp/llm/clients/__init__.py:10 · 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 addressMakefile:43 · 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
Access to sensitive file pathssrc/honeymcp/llm/clients/__init__.py:15 · 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

What would make this Verified

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim barvhaim: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Stripe-like API key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim barvhaim