Skynet Score
v1.0.0Use for searching CertiK Skynet project scores, looking up blockchain project security ratings, comparing score breakdowns, and integrating the public Skynet...
⭐ 0· 98·0 current·0 all-time
byCertiK@certik-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description claim searching CertiK Skynet scores and the included Python script + curl examples both directly call the documented public endpoint (https://open.api.certik.com/projects). No unrelated services, credentials, or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to run the bundled script or use curl against the documented API and to return/format API data. The instructions do not ask the agent to read arbitrary files, environment secrets, or system state beyond executing the script and issuing outbound HTTPS requests to the documented endpoint.
Install Mechanism
No install spec is present (instruction-only with a bundled script). The script is small, stored in the skill bundle, and there are no downloads from external URLs or archive extraction steps.
Credentials
The skill declares no required environment variables, no credentials, and the code does not read env vars or config paths. Network access to the public CertiK API is required and is proportional to the stated function.
Persistence & Privilege
The skill does not request always:true and does not attempt to modify other skill/system configs. It only asks permission to execute its bundled script at runtime.
Assessment
This skill appears to do exactly what it says: call the public CertiK Skynet projects endpoint and return results. Before installing, consider: (1) the skill will make outbound HTTPS requests to open.api.certik.com — if you run it in a sensitive environment, sandbox network access; (2) the skill owner is unknown (no homepage), so only run if you trust the registry/source or inspect the included script (which in this case is small and readable); (3) there are documented rate limits (50 requests/60s per IP) so avoid high-frequency automated polling; (4) the skill does not request credentials, but never provide unrelated secrets to skills. If you want stricter control, disable autonomous invocation so it only runs when you explicitly invoke it.Like a lobster shell, security has layers — review code before you run it.
latestvk97046wax02yp91f38zn4e0a3x832htj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.