Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill promises Caltech-related information and the SKILL.md contains only high-level content modules (history, scope, global layout, news) consistent with that purpose. It does not request unrelated resources, binaries, or credentials.
Instruction Scope
SKILL.md is short and high-level; it triggers on queries about Caltech and lists what to provide. It does not instruct reading local files, accessing secrets, or posting data to external endpoints. Note: because it is minimal, the agent may still perform web searches to gather content when invoked — that is expected but outside the skill's explicit instructions.
Install Mechanism
No install spec and no code files (instruction-only). Nothing is written to disk and no packages are pulled, which is the lowest-risk install pattern.
Credentials
The skill declares no required environment variables, credentials, or config paths — appropriate for a read-only informational skill.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or elevated privileges. Autonomous invocation (model calling the skill) is allowed by default but not combined with other red flags here.
Assessment
This skill appears coherent and low-risk: it only defines what Caltech topics to summarize and asks for no credentials or installs. Before relying on its output, verify the factual sources because the skill's publisher and homepage are unknown. If you need authoritative information, cross-check with Caltech's official website. If you want tighter control, keep the skill user-invocable (not always enabled) and monitor any web searches the agent performs when answering.Like a lobster shell, security has layers — review code before you run it.
latestvk977gw9h5pc2yny4gbtvsq01s184x1t8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.