pi-evox-loop@0.39.0
VERIFIED· install onlyPublisher claims: "Give your coding agent an 'experience inheritance' runtime: recall validated fixes from an Evolver gene store at task start, register hits when a fix is actually used, and deposit newly-learned fixes after repairing a non-obvious failure. Optionally run controlled closed-loop experiments (R1 trap → distill → inject → R2) to measure inheritance gains. Every fix is traced to its model/host and checked across models. Use at the START of non-trivial tasks, after fixing a non-obvious failure, or when you want to measure agent self-evolution. Trigger words: 经验召回, 错题本, 经验继承, 自进化, evolver, 避坑, distill." 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
What changed since 0.38.0
vet-skills diff pi-evox-loop 0.38.0 0.39.0This version reaches for something 0.38.0 did not: 2 new hosts (nodejs.org, qq.com) · 2 new credential variables (AGNES_CN_API_KEY, DEEPSEEK_API_KEY). Compared from the two recorded runs, not from source.
- New hosts
- nodejs.org, qq.com
- New credential variables
- AGNES_CN_API_KEY, DEEPSEEK_API_KEY
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 2026-11-08 and scored it 86/100 (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
const strategy = `${avoid} FIX: <在此填写可执行修法,例如 use encoding='gbk' / 先 chmod u+w 再写 / 先 ls 确认路径>`;Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.-----END PUBLIC KEY-----Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…nding vs quarantined vs approved), cwd-independent HITS_DIR, `install-snippet` (write the T1-T5 procedure into project AGENTS.md/CLAUDE.md - the deposit-side last mile), injection scan AVOID-context extension to high-r…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.// 2) 抽取含技术动作的片段(use/read with/open with/switch to/pass/set/chmod + 参数)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.修法:先恢复写权限(`chmod u+w config/settings.json`)再更新,最后可选恢复只读。Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.{ id: 'secret-exfil', sev: 'high', ctx: 'fix', re: /(读取|read|cat|dump|发(送|到|往)|include|propagate).{0,24}(密钥|token|凭证|credential|password|\.env|id_rsa|gitconfig|credential cache)/i },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…ATE\s+\w+\s+SET\b|\bpassword\b|\bpasswd\b|\btoken\b|\bapi[_-]?key\b|\bsecret\b|\.env\b|credentials|openclaw\.json|config\.yaml|MEMORY\.md|AGENTS\.md|SOUL\.md)/i; /…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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.