Multi Search Engine Jarvis
v2.0.2Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra...
⭐ 0· 73·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the manifest and SKILL.md: the skill is an instruction-only integration that builds search URLs for 17 engines and demonstrates web_fetch usage. There are no unrelated credentials, binaries, or install steps requested.
Instruction Scope
SKILL.md instructs the agent to call web_fetch on public search URLs and documents advanced operators and time filters. The instructions do not read local files, environment variables, or call unknown endpoints. Note: some examples/operators (e.g., intext:password filetype:txt) can be used to locate leaked or sensitive data — this is a legitimate search capability but a potential misuse vector driven by user queries, not hidden behavior in the skill.
Install Mechanism
No install spec and no code files to execute — instruction-only content. This is the lowest-risk install profile; nothing will be written to disk or fetched at install time.
Credentials
No environment variables, credentials, or config paths are requested. The declared manifest matches the runtime instructions (no secret exfiltration vectors declared).
Persistence & Privilege
always:false and default model-invocation settings. The skill does not request persistent/always-on privileges or modify other skills/config. Autonomous invocation is allowed by platform default but is not combined with any broad privileges here.
Assessment
This skill appears coherent and safe in scope: it simply generates and fetches public search URLs. Before installing, consider: (1) provenance — the source/homepage is unknown, so verify the publisher if you need trust guarantees; (2) privacy — any query you send (including sensitive strings) will be transmitted to the chosen search engine and may be logged by that service; avoid entering secrets or credentials into search queries; (3) misuse potential — advanced operators can locate leaked credentials or private information if used intentionally or inadvertently, so restrict who can invoke the skill and review usage logs if available. If you require stronger controls, test the skill in a sandboxed agent and avoid enabling autonomous invocation for untrusted users.Like a lobster shell, security has layers — review code before you run it.
latestvk97aeb1x1te4fen86t3z4s3gr183t6vs
License
MIT-0
Free to use, modify, and redistribute. No attribution required.