distillation-adversarial-verify@1.0.0
VERIFIED· install onlyPublisher claims: "跨模型蒸馏工程化的对抗验证环：对蒸馏出的关键决策规则 / 学生技能做反例测试，量化"学到了真能力 还是只学到表面话术"。给定一组规则(可调用函数或规则 dict)与对抗用例集，输出每条规则的健壮性 评分与整体蒸馏质量分，并标记需回炉的规则。纯标准库、零依赖、可本地实跑(--selftest 自带样例)。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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 463 lines in 6 files.
Cost to the agent
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.