extraction-agent-evaluation@1.0.0
VERIFIEDPublisher claims: "Design evidence-backed structured extraction workflows and evaluate field truth, grounding, record completeness and matching errors. Use for extraction schemas, agent evaluation and source-drift plans rather than source discovery or a whole dataset purchasing decision." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-04 and scored it 90/100 (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 deviationsStatic findings
No findings across 135 lines in 4 files.