pi-skill-subagent-governance@0.1.4
VERIFIEDPublisher claims: "Portable Agent Skill that governs one or more delegated children through role fit, plan-backed workers, one-writer isolation, handoffs, bounded retry safety, and reviewer finding disposition." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
$claude mcp add pi-skill-subagent-governance -- npx -y @firstpick/pi-skill-subagent-governance
WatchReport an issueIs [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-28 and scored it 93/100 (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 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
Static findings
CRITICAL
Prompt injectionskills/subagent-governance/references/PI-EXECUTION-ADAPTER.md:53 · Prompt injection — explicit attempt to bypass safety measuresFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01No other findings across 922 lines in 9 files.