70High
The skill risks command injection and SSRF due to uns
Behavior Analysis
Description verified — behavior matches claim
Claims to do
Web Search Plus: **Stop choosing search providers. Let the skill do it for you.**
Actually does
This skill executes Python scripts to perform web searches. It reads API keys from environment variables or a configuration file and uses them to make API calls to various search providers including Serper, Tavily, Querit, Exa, Kilo (for Perplexity), You.com, and a user-configured SearXNG instance. It automatically routes queries to the most suitable provider based on query analysis, and can fall back to other providers if one fails.
Skill Info
Namerobbyczgw-cla/web-search-plus
Registryclawhub
Version2.9.2
PURLpkg:clawhub/robbyczgw-cla/web-search-plus@2.9.2
Stars94
Downloads19,550
Installs153
Source
SHA-256f373cb312086...
SHA-132782b053092...
MD50eab9a2da9fc...
TLSHb1221babed11...
ssdeep192:uE+2d8Pf...
Size10,276 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
ClawHubDocs
openclaw skills install robbyczgw-cla/web-search-plusAssessments (2)
AI Agent Traps ↗Command Execution via User-Controlled Inputhighcommand execution
The skill explicitly requires `python3` and `bash` and invokes Python scripts (`scripts/search.py`) with user-provided query strings (`-q`) and other parameters. If these scripts do not properly sanitize user input before constructing shell commands or API requests, it could lead to arbitrary command execution.
80% confidenceline 6
metadata: {"openclaw":{"requires":{"bins":["python3","bash"]...}}}, `python3 scripts/search.py -q "Tesla Model 3 price"`Potential SSRF via Unprotected URL Parametersmediumssrf
The skill accepts user-provided URLs (e.g., `--similar-url` for the Exa provider). While SSRF protection is explicitly mentioned for the SearXNG instance URL, it is not stated for other providers or general URL handling, creating a potential SSRF vulnerability if not universally applied.
70% confidenceline 110
`python3 scripts/search.py -p exa --similar-url "https://stripe.com"`
Undisclosed Script Content for Core Functionalitylowdescription mismatch
The skill's core functionality relies on external Python scripts (`scripts/setup.py`, `scripts/search.py`) whose content is not provided for analysis. The security posture of the skill is highly dependent on the implementation details of these scripts, particularly regarding input sanitization and API key handling.
90% confidenceline 60
`python3 scripts/setup.py`, `python3 scripts/search.py -q "..."`
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/clawhub/robbyczgw-cla/web-search-plus)HTML
<a href="https://mondoo.com/ai-agent-security/skills/clawhub/robbyczgw-cla/web-search-plus"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/robbyczgw-cla/web-search-plus.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/clawhub/robbyczgw-cla/web-search-plus.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow