Multi Search Engine
Analysis
This instruction-only skill is purpose-aligned for web search, but users should notice that it sends queries to many external search engines and temporarily handles search-engine cookies.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Use web_fetch to execute search requests with rate limiting... Batch requests in groups of 3-4 engines... If access is denied (403/429), fetch engine homepage to obtain fresh session cookies
The skill instructs the agent to make automated requests to multiple search engines and retry with newly obtained session cookies. This is disclosed and aligned with search aggregation, but it can trigger provider blocks or terms-of-service issues if overused.
Registry version: 2.1.3; _meta.json version: 2.0.1; metadata.json version: 2.1.0; Source: unknown; Homepage: none
The package is instruction-only and has no install script, but the source is not identified and version metadata is inconsistent across supplied artifacts.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Cookies are stored ONLY in memory during runtime... No cookies are read from or written to config.json or any file... Only session cookies from search engine domains are captured
The skill handles temporary search-engine session cookies. The artifacts explicitly bound them to runtime memory and search-engine domains, with no local browser cookie or credential access described.
