gxpcode-translator@0.1.1
VERIFIED· install onlyPublisher claims: "专业翻译工具 — 支持文本和 PDF 输入，PDF 输出双语对照 HTML + Markdown。触发关键词：翻译、术语保护、更新术语、词典、glossary、保留特定词。" 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 2026-11-12 and scored it 82/100 (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
python Gxpcode_html.py --elements recognition.json --translated translated.txt --out-dir output/ --title "ISPE Guide"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.python Gxpcode_markdown.py --elements recognition.json --translated translated.json --out-dir output/ --title "ISPE Guide"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.<li>\u53cc\u680f\u5bf9\u7167\uff1a\u5de6\u5217\u539f\u6587\uff08EN\uff09\uff0c\u53f3\u5217\u8bd1\u6587\uff08ZH\uff09</li>Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Loads Gxpcode-dict.csv, builds automaton, scans text, outputs JSON.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.{Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.python build_page_text.py --elements recognition.json --page 16 [--output out.txt]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…875</span> <span class="tag">{ts}</span> </div> <div id="disclaimer">Gxpcode \u4ec5\u63d0\u4f9b\u4e13\u4e1a\u7ffb\u8bd1\u5de5\u5177\uff0c\u4e0d\u5bf9\u7ffb\u8bd1\u5185\u5bb9\u505a\u4efb\u4f55\u4fdd\u8bc1\u4e0e\u8d1f\u8d23<br>\u5982\u5bf9\u…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.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.