OpenClaw: suspicious
VirusTotal: benign
StaticScan: unknown
OpenClaw: suspicious
The skill's instructions broadly match a runtime hardening purpose, but naming inconsistencies, an embedded prompt-injection pattern, and the unknown origin make the package suspicious and worth manua... [内容已截断]
VirusTotal: benign VT 报告
静态扫描: unknown
README 未提供
无文件信息
{
"latestVersion": {
"_creationTime": 1770996744406,
"_id": "k97fbc6fxgvr08a03sjdd9wws58129fx",
"changelog": "Initial release: Adds carapace runtime hardening for OpenClaw agents.\n\n- Provides defense against prompt injection, data exfiltration, credential leaks, and unauthorized operations.\n- Enforces explicit confirmation for sensitive actions (file writes, execs, config changes, external navigation).\n- Introduces strict credential and data sharing protections, with exceptions only for explicit owner requests.\n- Supplies implementation resources: security rules for AGENTS.md, audit template, and reference attack patterns.\n- Supports browser allowlisting for domain-level navigation controls.",
"changelogSource": "auto",
"createdAt": 1770996744406,
"version": "1.0.0"
},
"owner": {
"_creationTime": 0,
"_id": "publishers:missing",
"displayName": "EridianCarapace",
"handle": "iampaulpatterson-boop",
"image": "https:\/\/avatars.githubusercontent.com\/u\/228373334?v=4",
"kind": "user",
"linkedUserId": "kn7901tapfjwef2efk6gr6r7b9813st8"
},
"ownerHandle": "iampaulpatterson-boop",
"skill": {
"_creationTime": 1770996744406,
"_id": "kd7etbb23hykhqkk9fz0bwmvnh812vwd",
"badges": [],
"createdAt": 1770996744406,
"displayName": "Eridian",
"latestVersionId": "k97fbc6fxgvr08a03sjdd9wws58129fx",
"ownerUserId": "kn7901tapfjwef2efk6gr6r7b9813st8",
"slug": "eridian",
"stats": {
"comments": 0,
"downloads": 566,
"installsAllTime": 1,
"installsCurrent": 1,
"stars": 0,
"versions": 1
},
"summary": "Runtime security hardening for OpenClaw agents. Protects against prompt injection, data exfiltration, credential leaks, and unauthorized operations. Use when setting up agent security, performing security audits, protecting credentials, preventing data leaks, hardening agent configurations, or defending against indirect prompt injection attacks. Complements pre-installation skill scanners by hardening the agent itself at runtime.",
"tags": {
"latest": "k97fbc6fxgvr08a03sjdd9wws58129fx"
},
"updatedAt": 1772337686965
}
}