OpenClaw: suspicious
VirusTotal: suspicious
StaticScan: unknown
OpenClaw: suspicious
The skill is generally coherent with its stated purpose (orchestrating coding CLIs via exec/process) but contains a few mismatches and risky instructions (flags that bypass permissions, open-ended com... [内容已截断]
VirusTotal: suspicious VT 报告
静态扫描: unknown
README 未提供
无文件信息
{
"latestVersion": {
"_creationTime": 1770354202802,
"_id": "k9791380adwhbksfkd4sazetad80mrcx",
"changelog": "Version 1.1.0 summary: Expanded documentation and feature guidance for Ralph Loop agent orchestration.\n\n- Added comprehensive SKILL.md detailing agent workflows, tool usage, prompts, and best practices.\n- Documented support for interactive CLIs with proper TTY and background process management.\n- Outlined PLANNING vs BUILDING loop modes, completion condition detection, and sandboxing safeguards.\n- Included explicit input requirements, command templates for major AI coding agents, and troubleshooting guidance.\n- Emphasized use of exec+process tools for robust automation and session control.",
"changelogSource": "auto",
"createdAt": 1770354202802,
"version": "1.1.0"
},
"owner": {
"_creationTime": 0,
"_id": "publishers:missing",
"displayName": "addozhang",
"handle": "addozhang",
"image": "https:\/\/avatars.githubusercontent.com\/u\/2224492?v=4",
"kind": "user",
"linkedUserId": "kn7bwka6wky0wqckspmy7nwrps80nwqj"
},
"ownerHandle": "addozhang",
"skill": {
"_creationTime": 1770354202802,
"_id": "kd7739f93t3j13zeqtrmg4k1tx80n19z",
"badges": [],
"createdAt": 1770354202802,
"displayName": "Ralph Loop (Agent Mode)",
"latestVersionId": "k9791380adwhbksfkd4sazetad80mrcx",
"ownerUserId": "kn7bwka6wky0wqckspmy7nwrps80nwqj",
"slug": "ralph-loop-agent",
"stats": {
"comments": 2,
"downloads": 2233,
"installsAllTime": 11,
"installsCurrent": 11,
"stars": 0,
"versions": 1
},
"summary": "Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans\/builds code via PROMPT.md + AGENTS.md, SPECS and IMPLEMENTATION_PLAN.md. Includes PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions. Users request loops, agents execute using tools.",
"tags": {
"latest": "k9791380adwhbksfkd4sazetad80mrcx"
},
"updatedAt": 1774322960887
}
}