openlx-ctrip-hotel-ops@0.1.1
VERIFIED· install onlyPublisher claims: "经营体检、点评回复、房价房态与笔记生产，按真实证据记录每项执行结果" Observed in sandbox: reads credential files.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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 (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-07 and scored it 87/100 (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: reads credential files.
Behavior trace
Honeypot run · 3 s · 2 scenariost+CategoryObserved action
1.3sfilesystemread ~/.codex/skills/openlx-ctrip-hotel-ops/package.json · ~/.codex/skills/openlx-ctrip-hotel-ops/package-lock.json · ~/.codex/skills/openlx-ctrip-hotel-ops/yarn.lock · ~/.codex/skills/openlx-ctrip-hotel-ops/node_modules · ~/.codex/skills/openlx-ctrip-hotel-ops/node_modules/.package-lock.json · ~/.codex/skills/openlx-ctrip-hotel-ops/node_modules/playwright-core/package.json outside project
1.3sfilesystemwrote ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/daemon.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/browser.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/automation.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/ops.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/notes.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/model.mjs
1.3snetworkCONNECT https://registry.npmjs.org
1.3snetworkCONNECT https://registry.npmjs.org
1.3sprocessexec /app/apps/web/node_modules/.bin/npm
1.3sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/npm
1.3sprocessexec /app/node_modules/.bin/npm
1.3sprocessexec /pnpm/npm
1.3sprocessexec /usr/local/sbin/npm
1.3sprocessexec /usr/local/bin/npm
1.3sprocessexited 1: {"status":"FAILED","error":"依赖安装失败，请检查Node/npm与网络","backup":null,"target":"/tmp/ks-detonate-oYqVC1/setup/home/.codex/skills/openlx-ctrip-hotel-ops","next":"保留诊断目录；修复后重试，或用rollback恢复旧版本"}
1.3sprocessscript backend runs setup only
1.3sprocessscript backend runs setup only
1.6sprocesssecond launch, clock +45 days, CI unset
2.5sfilesystemread ~/.codex/skills/openlx-ctrip-hotel-ops/.npmrc · ~/.npmrc
2.5sfilesystemread ~/.npm/_logs · ~/.codex/skills/openlx-ctrip-hotel-ops/package.json · ~/.codex/skills/openlx-ctrip-hotel-ops/npm-shrinkwrap.json · ~/.codex/skills/openlx-ctrip-hotel-ops/package-lock.json · ~/.codex/skills/openlx-ctrip-hotel-ops/yarn.lock · ~/.codex/skills/openlx-ctrip-hotel-ops/node_modules outside project
2.5sfilesystemwrote ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/daemon.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/browser.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/automation.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/ops.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/notes.mjs · ~/.codex/skills/openlx-ctrip-hotel-ops/scripts/model.mjs
2.5snetworkCONNECT https://registry.npmjs.org
2.5snetworkCONNECT https://registry.npmjs.org
2.5snetworkCONNECT https://registry.npmjs.org
2.5sprocessexec /usr/bin/faketime
2.5sprocessexec /app/apps/web/node_modules/.bin/npm
2.5sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/npm
2.5sprocessexec /app/node_modules/.bin/npm
2.5sprocessexec /pnpm/npm
2.5sprocessexec /usr/local/sbin/npm
2.5sprocessexec /usr/local/bin/npm
2.5sprocessexited 1: {"status":"FAILED","error":"依赖安装失败，请检查Node/npm与网络","backup":"/tmp/ks-detonate-oYqVC1/later/home/.codex/skills/.openlx-ctrip-hotel-ops-backups/1797956871932","target":"/tmp/ks-detonate-oYqVC1
Static findings
LOW
False input termination markerassets/license-public.txt:3 · False input termination marker — attempts to end user input section · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file
AST01-----END PUBLIC KEY-----Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.No other findings across 4,772 lines in 24 files.
Cost to the agent
Instructions loaded
≈609 tok
1 file · 24 in bundle
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.