Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Remindy
v1.0.0Email and browser push notification reminders delivered 15 minutes before scheduled events.
⭐ 0· 20·0 current·0 all-time
byToolWeb@krishnakumarmahadevan-cmd
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description match the included API docs (endpoints for creating/listing reminders, push subscription, VAPID key). However the package provides only documentation (no host URL, no security scheme, no required credentials) while the pricing and hosted-service language imply an external, authenticated API. A real production reminder service would normally publish a base server URL and an authentication mechanism (API key, OAuth) — their absence is unexpected.
Instruction Scope
SKILL.md is a specification-style usage doc and does not instruct the agent to read local files, environment variables, or system state, nor to run shell commands. It stays within the scope of describing HTTP endpoints and request/response shapes. However the docs reference relative endpoints (e.g., /api/reminders/create) without a base URL, which would force an agent or integrator to guess or request a host, creating ambiguity.
Install Mechanism
There is no install specification and no code files to be written to disk. Instruction-only skills are lower risk; nothing is downloaded or installed by the skill itself.
Credentials
The skill declares no required environment variables or credentials. That is reasonable for a pure documentation/spec asset, but surprising for a service that sends email and push notifications: production use normally requires API keys, SMTP credentials, or similar secrets. The lack of declared auth could lead integrators or agents to supply credentials in an ad-hoc way, which is risky.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. It does not request system or other-skill configuration modifications. Autonomous invocation is allowed by default but is not combined with other high-privilege requests here.
What to consider before installing
This skill appears to be API documentation for a hosted reminder service rather than runnable code; however important trust and operational details are missing. Before installing or using it: 1) Ask the publisher for the service base URL and an explanation of how authentication is performed (API key, OAuth, etc.). Do not paste secrets into chat. 2) Verify the publisher/source (there is no homepage and source is unknown); prefer skills from known providers. 3) If you plan to integrate, test against a staging/dummy account first and confirm TLS and authentication. 4) Treat any prompts from the agent requesting credentials or tokens as sensitive — prefer to provide short-lived tokens and revoke them after testing. 5) If you need a hosted reminder service, consider a provider with documented security (privacy policy, contact, and published base URLs) or implement server-side components under your control. These gaps make the skill suspicious but not definitively malicious; additional information about the service operator and its authentication model would raise confidence.Like a lobster shell, security has layers — review code before you run it.
latestvk972tzb0x0b55z5kvt4jgzn3bn8494kt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.