Skills/ClawHub/system-prompt-guardrails

system-prompt-guardrails@1.0.0

VERIFIED

Publisher claims: "Add ethical guardrails to a system prompt, SOUL.md, AGENTS.md, CLAUDE.md or any agent instructions file. Three questions (what the agent will never do, what wins when values conflict, who can change the rules) become one GROUND block at the top of the file. Works offline; publishing to botsmatter.live is optional. Use when writing or editing a system prompt or agent instructions, or when the user asks to add rules, boundaries, values or guardrails to an agent." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher achurchai · joined 5 days agoInstalls 241Last detonated 4d ago
$clawhub install system-prompt-guardrails
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-29 and scored it 84/100 (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
0.0sprocessscript backend runs setup only

Static findings

CRITICAL
Prompt injectionSKILL.md:182 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:3 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01