Skills/npm/prompt-architect

prompt-architect@3.5.1

VERIFIED

Publisher claims: "Agent skill for analyzing and improving prompts using 31 frameworks across 7 intent categories. Works with Claude Code, Gemini CLI, Cursor, Copilot, and 30+ Agent Skills compatible tools." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ckelsoe · joined 7 days agoInstalls 212Last detonated 7d ago
$claude mcp add prompt-architect -- npx -y @ckelsoe/prompt-architect
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 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 · 0 s · 1 scenarios
t+CategoryObserved action
0.1sfilesystemwrote ~/.agents/skills/prompt-architect/SKILL.md · ~/.agents/skills/prompt-architect/assets/templates/ape_template.txt · ~/.agents/skills/prompt-architect/assets/templates/bab_template.txt · ~/.agents/skills/prompt-architect/assets/templates/broke_template.txt · ~/.agents/skills/prompt-architect/assets/templates/cai-critique-revise_template.txt · ~/.agents/skills/prompt-architect/assets/templates/care_template.txt
0.1sprocessexec /usr/bin/which
0.2sfilesystemread ~/.agents/skills/prompt-architect · ~/.agents/skills/prompt-architect/assets · ~/.agents/skills/prompt-architect/assets/templates · ~/.agents/skills/prompt-architect/references · ~/.agents/skills/prompt-architect/references/frameworks · ~/.agents/skills/prompt-architect/references/techniques outside project
0.2sfilesystemwrote ~/.agents/skills/prompt-architect/SKILL.md · ~/.agents/skills/prompt-architect/assets/templates/ape_template.txt · ~/.agents/skills/prompt-architect/assets/templates/bab_template.txt · ~/.agents/skills/prompt-architect/assets/templates/broke_template.txt · ~/.agents/skills/prompt-architect/assets/templates/cai-critique-revise_template.txt · ~/.agents/skills/prompt-architect/assets/templates/care_template.txt
0.2sprocessexec /usr/bin/which
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only

Static findings

CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/crispe.md:151 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/risen.md:96 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/crispe.md:119 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/rise.md:279 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/crispe.md:185 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/assets/templates/tidd-ec_template.txt:12 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/crispe.md:89 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/assets/templates/crispe_template.txt:13 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/assets/templates/risen_template.txt:11 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/rise.md:321 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/assets/templates/rise-ix_template.txt:4 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/risen.md:136 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagescripts/install.js:12 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.js:13 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/build-skill.js:64 · 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
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/tidd-ec.md:121 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagescripts/install.js:11 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/install.js:236 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/build-skill.js:63 · 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
npx invocation of non-well-known packagescripts/install.js:237 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/tidd-ec.md:197 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionscripts/build-skill.js:65 · 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
CRITICAL
Rule addition attemptskills/prompt-architect/references/frameworks/tidd-ec.md:455 · Rule addition attempt — injecting new instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
System prompt continuationskills/prompt-architect/references/frameworks/risen.md:179 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
prompt-architect@3.5.1 safety verdict: Verified 80/100 — KillerSkills