Item detail

jnMetaCode/shellward

jnMetaCode/shellward is an Apache-2.0 zero-dependency security and compliance gateway for agent workflows, combining project scans with runtime defenses against prompt injection, risky commands, data exfiltration paths, and China-focused AI compliance issues across MCP, SDK, and plugin setups.

Score8.3
Popularity10.0
Riskconditional
TierSilver
Score breakdown
Usefulness8.0
Novelty8.0
Momentum6.0
Maturity6.2
Open-source/build8.4
Evidence7.2
Workflow potential9.4
Setup ease4.2

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for teams that are moving agents closer to real data and real actions and want something more concrete than vague 'guardrails' talk.

Who should use it

teams deploying MCP or coding-agent workflows in regulated environmentssecurity engineers reviewing agent tool accessbuilders who want prompt-injection and DLP checks in one layerorganizations that need China-specific compliance signals alongside runtime defenses

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

It sits inline on prompts, tool calls, and potentially sensitive data, so deployment location, logging, and policy tuning matter as much as the default rules.

Evidence links

Closest alternatives / related signals

securityguardrailsprompt-injectiondlpcompliance