needle-mcp@r2

VERIFIED

Publisher claims: "Production-ready RAG service to search and retrieve data from your documents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Docker MCP CatalogPublisher needle-ai · joined 10 days agoInstalls 12,132Last detonated 2 h ago

$docker run -i --rm mcp/needle-mcp

Watch Report an issue

Is needle-mcp@r2 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-05 and scored it 86/100 (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 · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

Static findings

LOW

Prompt injectionREADME.md:74 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.

AST01

LOW

Authorization escalation languageREADME.md:74 · Authorization escalation language · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.

AST01

HIGH

Access to sensitive file pathsskills/needle/SKILL.md:269 · 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

LOW

Prompt injectionREADME.md:72 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.

AST01

LOW

Authorization escalation languageREADME.md:72 · Authorization escalation language · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.

AST01

Cost to the agent

Instructions loaded

≈8,593 tok

1 file · 4 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.