# Send Openclaw Warden to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "openclaw-warden", "name": "Openclaw Warden", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/AtlasPA/openclaw-warden", "canonicalUrl": "https://clawhub.ai/AtlasPA/openclaw-warden", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/openclaw-warden", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-warden", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "scripts/integrity.py", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "openclaw-warden", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T18:42:48.055Z", "expiresAt": "2026-05-07T18:42:48.055Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-warden", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-warden", "contentDisposition": "attachment; filename=\"openclaw-warden-1.0.3.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "openclaw-warden" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/openclaw-warden" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/openclaw-warden", "downloadUrl": "https://openagent3.xyz/downloads/openclaw-warden", "agentUrl": "https://openagent3.xyz/skills/openclaw-warden/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-warden/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-warden/agent.md" } } ``` ## Documentation ### OpenClaw Warden Monitors your workspace files for unauthorized modifications and prompt injection attacks. Existing security tools scan skills before installation — this tool watches the workspace itself after installation, catching tampering that other tools miss. ### Why This Matters Your agent reads SOUL.md, AGENTS.md, IDENTITY.md, USER.md, and memory files on every session startup and trusts them implicitly. A compromised skill, a malicious heartbeat payload, or an unauthorized process can modify these files to: Inject hidden instructions that alter agent behavior Embed data exfiltration URLs in markdown images Override identity and safety boundaries Plant persistent backdoors in memory files This skill detects all of these. ### Establish Baseline Create or reset the integrity baseline. Run this after setting up your workspace or after reviewing and accepting all current file states. python3 {baseDir}/scripts/integrity.py baseline --workspace /path/to/workspace ### Verify Integrity Check all monitored files against the stored baseline. Reports modifications, deletions, and new untracked files. python3 {baseDir}/scripts/integrity.py verify --workspace /path/to/workspace ### Scan for Injections Scan workspace files for prompt injection patterns: hidden instructions, base64 payloads, Unicode tricks, markdown image exfiltration, HTML injection, and suspicious system prompt markers. python3 {baseDir}/scripts/integrity.py scan --workspace /path/to/workspace ### Full Check (Verify + Scan) Run both integrity verification and injection scanning in one pass. python3 {baseDir}/scripts/integrity.py full --workspace /path/to/workspace ### Quick Status One-line summary of workspace health. python3 {baseDir}/scripts/integrity.py status --workspace /path/to/workspace ### Accept Changes After reviewing a legitimate change, update the baseline for a specific file. python3 {baseDir}/scripts/integrity.py accept SOUL.md --workspace /path/to/workspace ### Workspace Auto-Detection If --workspace is omitted, the script tries: OPENCLAW_WORKSPACE environment variable Current directory (if AGENTS.md exists) ~/.openclaw/workspace (default) ### What Gets Monitored CategoryFilesAlert Level on ChangeCriticalSOUL.md, AGENTS.md, IDENTITY.md, USER.md, TOOLS.md, HEARTBEAT.mdWARNINGMemorymemory/*.md, MEMORY.mdINFO (expected to change)Config*.json in workspace rootWARNINGSkillsskills/*/SKILL.mdWARNING Injection patterns trigger CRITICAL alerts regardless of file category. ### Injection Patterns Detected Instruction override: "ignore previous instructions", "disregard above", "you are now", "new system prompt" Base64 payloads: Suspiciously long base64 strings outside code blocks Unicode manipulation: Zero-width characters, RTL overrides, homoglyphs Markdown exfiltration: Image tags with data-encoding URLs HTML injection: script tags, iframes, hidden elements System prompt markers: , [SYSTEM], <> blocks Shell injection: $(...) outside code blocks ### Exit Codes 0 — Clean, no issues 1 — Modifications detected (review needed) 2 — Injection patterns detected (action needed) ### No External Dependencies Python standard library only. No pip install. No network calls. Everything runs locally. ### Cross-Platform Works with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: AtlasPA - Version: 1.0.3 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-30T18:42:48.055Z - Expires at: 2026-05-07T18:42:48.055Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/openclaw-warden) - [Send to Agent page](https://openagent3.xyz/skills/openclaw-warden/agent) - [JSON manifest](https://openagent3.xyz/skills/openclaw-warden/agent.json) - [Markdown brief](https://openagent3.xyz/skills/openclaw-warden/agent.md) - [Download page](https://openagent3.xyz/downloads/openclaw-warden)