aiarchitect-blog-mcp@0.1.1
VERIFIEDPublisher claims: "MCP server that exposes the AI아키텍트 (aiarchitect.tistory.com) technical blog — 69 articles — as searchable tools for AI agents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher aiarchitecturedev · joined 0 days agoInstalls 60Last detonated 2 h ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-26 and scored it 88/100 (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 · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/aiarchitect-blog-mcp
0.2sprocessexited 127: timeout: failed to run command '.venv/bin/aiarchitect-blog-mcp': No such file or directory
0.2sclaimedno tools/list reply (exit 127)
0.2sprocessscript backend runs setup only
Static findings
CRITICAL
Prompt injectionsrc/aiarchitect_blog_mcp/data/articles/47-remote-mcp-six-clients-oauth-discovery.md:105 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionsrc/aiarchitect_blog_mcp/data/articles/23-prompt-injection-trust-boundaries-tool-allowlist.md:39 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionsrc/aiarchitect_blog_mcp/data/articles/23-prompt-injection-trust-boundaries-tool-allowlist.md:35 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionsrc/aiarchitect_blog_mcp/data/articles/47-remote-mcp-six-clients-oauth-discovery.md:167 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01HIGH
Authorization escalation languagesrc/aiarchitect_blog_mcp/data/articles/47-remote-mcp-six-clients-oauth-discovery.md:105 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Authorization escalation languagesrc/aiarchitect_blog_mcp/data/articles/47-remote-mcp-six-clients-oauth-discovery.md:167 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Fake instruction boundary tagsrc/aiarchitect_blog_mcp/data/articles/53-software-supply-chain-dependencies-sbom-signing-release-gate.md:182 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01CRITICAL
Fake instruction boundary tagsrc/aiarchitect_blog_mcp/data/articles/53-software-supply-chain-dependencies-sbom-signing-release-gate.md:187 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01