Skills/npm/god-prompt-mcp

god-prompt-mcp@1.4.2

VERIFIED

Publisher claims: "GodPrompt MCP server + portable Agent Skill for coding agents — TDD, debugging, verification gates, task routing, and progressive disclosure." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher akzar1el · publishing for 84 daysInstalls 6,404Last detonated 14 min ago
$claude mcp add god-prompt-mcp -- npx -y god-prompt-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
GITHUB_TOKENConfiguration, not credentials: GODPROMPT_CODEXIFY_AUDIT_CONVERSATION_ID, GODPROMPT_CODEXIFY_AUDIT_FILE, GODPROMPT_CODEXIFY_AUDIT_NOT_BEFORE, GODPROMPT_CODEXIFY_AUDIT_PROJECT_ID, GODPROMPT_FEEDBACK_FILE, XDG_STATE_HOME
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for GITHUB_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --net declared -- npx -y god-prompt-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.1.1

vet-skills diff god-prompt-mcp 1.1.1 1.4.2

This version reaches for something 1.1.1 did not: 13 new tools (assess_release_readiness, audit_agent_instructions, audit_agent_trajectory, audit_requirements, …) · 1 rewritten tool descriptor (get_god_prompt). Compared from the two recorded runs, not from source.

New tools
assess_release_readiness, audit_agent_instructions, audit_agent_trajectory, audit_requirements, build_test_matrix, compare_evaluation_runs, create_context_handoff, design_adversarial_tests, diagnose_failure, get_tailored_guidance, review_code_change, review_mcp_tool_contracts +1
Rewritten tool descriptors
get_god_prompt

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-22 and scored it 80/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 31 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
11sprocessdependency install exit 0
31sclaimed22 tools: get_god_prompt, get_core_skill, get_protocols, get_gates, get_anti_patterns, classify_task, get_version, create_work_contract, review_work_evidence, review_code_change, audit_requirements, build_test_matrix, get_tailored_guidance, diagnose_failure, assess_release_readiness, create_context_handoff, compare_evaluation_runs, audit_agent_trajectory, trace_change_impact, review_mcp_tool_contracts, audit_agent_instructions, design_adversarial_tests
31stools60febb0591978136
31stools8440175e636ba5ec
31stools95457aaba16bf6d0
31stoolsbec6d5963980b930
31stools47f7cf7978795f25
31stools73cafe5243559723
31stools79df40925e175a23
31stools4792f1f1d8cd0684
31stools13b171d0e511e1be
31stools05ed4c53a123a339
31stoolsdb3a477d99674b6d
31stoolsa05d58047bb1d83a
31stools1a36beba09f7eda7
31stools1043c9f12e784937
31stoolsb79072a28c7cedf8
31stools69a081a272db55de
31stools411cd52e4d28b5cb
31stoolsc0e2c3d275a3a567
31stools943cd96906fe2a4c
31stools4215e601644dd82e
31stoolsb6d856a1d192194a
31stools0e84bd43450977b8
31sprocessscript backend runs setup only
31sprocessno install scripts to re-run

Static findings

HIGH
Destructive file system command detecteddist/content.js:968 · Destructive file system command detected### Fix Report FormatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detecteddist/content.js:933 · Destructive file system command detected### Commit Message FormatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsdist/stdio.js:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn runtime.process?.env?.GODPROMPT_CODEXIFY_CHECKPOINT === "1";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 pathsdist/content.js:2128 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- [ ] .env.example file with all required variablesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/content.js:1149 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- [ ] .env.example file with all required variablesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionREADME.md:104 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. Open **Plugins**, select **+**, then **Add custom MCP server**. The current Plugins flow does **not** require Developer Mode.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Destructive file system command detecteddist/content.js:1912 · Destructive file system command detected### Commit Message FormatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsdist/content.js:2116 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- [ ] All config via environment variables (.env file)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 pathsdist/content.js:1137 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- [ ] All config via environment variables (.env file)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detecteddist/content.js:1947 · Destructive file system command detected### Fix Report FormatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageREADME.md:104 · Authorization escalation language · informational: not an instruction file1. Open **Plugins**, select **+**, then **Add custom MCP server**. The current Plugins flow does **not** require Developer Mode.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈72 tok
1 file · 24 in bundle
Tool list per prompt
≈4,740 tok
22 tools · 215 per tool
Handshake
1324 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 236

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

Not checked against OSV yet; the weekly check has not reached this version.