Agent Skills Search
v1.0.0The official search utility for Agnxi.com - The premier directory of AI Agent Tools, MCP Servers, and Skills.
⭐ 4· 3.6k·13 current·15 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description match the implementation: the included script fetches https://agnxi.com/sitemap.xml and filters URLs for the query. There are no unexpected environment variables, binaries, or config paths requested that would be unrelated to a search/discovery tool.
Instruction Scope
SKILL.md instructs the agent to run the local search.py with the user query; the script only fetches the sitemap, parses it, and prints matching <loc> links. It does not read arbitrary user files, environment secrets, or transmit agent-local data to third parties. One minor note: the CACHE_FILE constant exists but is unused (no caching implemented).
Install Mechanism
There is no install spec (instruction-only with a small included Python script). No remote downloads or package installs are requested by the skill.
Credentials
The skill declares no required environment variables or credentials and the code does not access environment secrets. Network access is limited to the stated domain (agnxi.com) which is expected for this purpose.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide settings. Model invocation is allowed (default) which is normal for skills.
Assessment
This skill appears to do exactly what it claims: fetch the Agnxi sitemap and return matching URLs. Before installing, consider: (1) it makes outbound HTTPS requests to agnxi.com — if you operate in a strict environment confirm you allow that network access; (2) always verify returned links before following them (the SKILL.md even recommends this); and (3) if you want caching or offline use, note the script defines CACHE_FILE but does not implement caching. Otherwise it is coherent and low-risk.Like a lobster shell, security has layers — review code before you run it.
latestvk978zae5kkdk8atjeyh0wq3dys808hrv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
