# Send Safe-Web 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": "safe-web", "name": "Safe-Web", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/AdamNaghs/safe-web", "canonicalUrl": "https://clawhub.ai/AdamNaghs/safe-web", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/safe-web", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=safe-web", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md", "scripts/safe-web.py", "skill.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "safe-web", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-08T09:21:15.574Z", "expiresAt": "2026-05-15T09:21:15.574Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=safe-web", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=safe-web", "contentDisposition": "attachment; filename=\"safe-web-1.0.8.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "safe-web" }, "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/safe-web" }, "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/safe-web", "downloadUrl": "https://openagent3.xyz/downloads/safe-web", "agentUrl": "https://openagent3.xyz/skills/safe-web/agent", "manifestUrl": "https://openagent3.xyz/skills/safe-web/agent.json", "briefUrl": "https://openagent3.xyz/skills/safe-web/agent.md" } } ``` ## Documentation ### safe-web Secure web fetch and search with PromptGuard scanning. ### Status ✅ Working ### Purpose Protects against prompt injection attacks hidden in web content before returning it to the AI. Wraps web fetching and searching with security scanning. ### Installation Requires PromptGuard and Python dependencies: # Install PromptGuard first cd /home/linuxbrew/.openclaw/workspace/skills/prompt-guard pip3 install --break-system-packages -e . # Install web dependencies (if not present) pip3 install --break-system-packages requests beautifulsoup4 ### Fetch Command Fetch a URL and scan the content: # Basic fetch safe-web fetch https://example.com/article # Save to file safe-web fetch https://example.com --output article.txt # JSON output for automation safe-web fetch https://example.com --json # Strict mode (block on MEDIUM) safe-web fetch https://example.com --strict ### Search Command Search the web and scan results: # Basic search safe-web search "AI safety research" # More results safe-web search "stock market news" --count 10 # JSON output safe-web search "machine learning" --json ### Exit Codes CodeMeaning0Success - content/results are clean1Error (network, parsing, etc.)2Threat detected - content blocked ### Environment Variables BRAVE_API_KEY - API key for Brave Search (optional, enables search command) Get one at: https://brave.com/search/api/ ### Symlink (Recommended) Create a system-wide symlink so safe-web works from any directory: sudo ln -s /home/linuxbrew/.openclaw/workspace/skills/safe-web/scripts/safe-web.py /usr/local/bin/safe-web After creating the symlink, you can use safe-web directly without specifying the full path. ### Fetch Flow Downloads URL content with requests Extracts text using BeautifulSoup (removes scripts, styles) Scans extracted text with PromptGuard Returns clean content or blocks with SHIELD report ### Search Flow Queries Brave Search API (requires API key) Scans each result title and description Filters out suspicious results Returns only clean results ### Security Model Fail-closed: If PromptGuard cannot be loaded or scanning fails, the tool reports an error rather than returning unverified content. Content sanitization: HTML is parsed and scripts/styles are removed before scanning to reduce false positives. No execution: This tool only fetches and scans. It never executes JavaScript or runs commands found in web content. ### Clean Fetch Fetching: https://site.com/article Fetched 1523 characters Scanning with PromptGuard... Article content here... ### Blocked Content Fetching: https://suspicious-site.com Fetched 2048 characters Scanning with PromptGuard... ============================================================ 🛡️ SAFE-WEB SECURITY ALERT ============================================================ Source: https://suspicious-site.com Severity: CRITICAL Action: BLOCK_NOTIFY Patterns Matched: 8 Detected Patterns: - instruction_override_en - role_manipulation_en - system_impersonation_en ============================================================ Content from https://suspicious-site.com has been blocked. ### Search Results Searching: AI research Found 5 results, scanning... Showing 3 clean results: 1. Latest AI Research Papers URL: https://arxiv.org/list/ai/recent Recent submissions in artificial intelligence... 2. AI Safety Institute URL: https://www.safe.ai/ Research and development for safe AI systems... ### When to Use Use safe-web when: Fetching content from untrusted URLs Scraping web pages for analysis Searching and processing web results Any web content will enter the AI context window Use standard web_fetch/web_search tools only for: Trusted, known-safe domains Internal documentation sites When you explicitly want to bypass scanning ### Comparison with Native Tools FeatureNative web_fetchsafe-web fetchFetches HTML✅✅Extracts text✅✅Injection scanning❌✅JSON output✅✅Save to file❌✅Exit codes0/10/1/2 (security) ### Dependencies Python 3.8+ PromptGuard 3.1.0+ (installed in workspace) requests beautifulsoup4 Brave Search API key (for search command) ### Limitations Search requires Brave API key (free tier available) Fetch does not execute JavaScript (static HTML only) Large pages may be truncated during text extraction Network timeouts default to 30 seconds ## Trust - Source: tencent - Verification: Indexed source record - Publisher: AdamNaghs - Version: 1.0.8 ## 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: 2026-05-08T09:21:15.574Z - Expires at: 2026-05-15T09:21:15.574Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/safe-web) - [Send to Agent page](https://openagent3.xyz/skills/safe-web/agent) - [JSON manifest](https://openagent3.xyz/skills/safe-web/agent.json) - [Markdown brief](https://openagent3.xyz/skills/safe-web/agent.md) - [Download page](https://openagent3.xyz/downloads/safe-web)