web-claude

Unified web search skill. Fallback order — web_search(Brave) → duckduckgo → claude.ai. Auto-cache search results (saved to memory/research/)

This skill appears to do what it says (a 3-tier unified search) but it omits some important declarations and assumptions. Before installing or using it: (1) Confirm where and how you will supply a Brave API key (the SKILL.md says it's required but the skill metadata doesn't declare it). Store that key in a secure place and avoid embedding it in logs. (2) Be aware the DuckDuckGo fallback uses a python snippet that requires the duckduckgo_search package and a Python runtime — install and vet that package if you plan to rely on it. (3) Tier 3 automates your local OpenClaw browser (port 18800) and requires a logged-in claude.ai session; automation will interact with your authenticated browser and could expose session-contained data — only enable it if you trust the skill and want automated access to your session. (4) The skill auto-saves search results to memory/research/ — these files may contain sensitive queries or fetched content; review and control that folder or request an option to disable caching. (5) Ask the skill author to update metadata to explicitly list required env vars, dependencies, and the cache path (so you can audit and control them). If you need higher assurance, request a version that declares dependencies and briefly shows the exact commands it will run (or provide an install script that you can review).

Type: OpenClaw Skill Name: web-claude Version: 1.1.0 The skill is classified as suspicious due to significant vulnerabilities that could lead to remote code execution (RCE) and arbitrary file writes. The `python -c` command used for DuckDuckGo search in SKILL.md presents a shell/Python injection risk if the search query is not properly sanitized. Additionally, the auto-caching feature, which creates files with `[keyword]` derived from the search query in `memory/research/`, introduces a path traversal or arbitrary file write vulnerability if the keyword is not sanitized. While the skill's stated purpose is benign, these implementation flaws allow for potential exploitation, classifying it as suspicious rather than malicious, as there's no clear evidence of intentional harmful design.