Build a concise “what needs action now” daily brief by aggregating reminders from multiple channels (email, calendar, SMS/iMessage, weather, and task notes)...
Security Analysis
medium confidenceThe skill's requested resources and instructions align with its stated purpose of aggregating reminders; it is an instruction-only skill with no installs or secret requests, but it implicitly relies on the agent's existing connectors (email/calendar/SMS) and its provenance is unknown so exercise normal caution.
The name/description (aggregate reminders from email, calendar, SMS, weather, tasks) matches the SKILL.md instructions. The skill does not request any environment variables, binaries, or install artifacts—which is coherent if the platform supplies connectors for email/calendar/SMS—but the metadata doesn't declare any explicit credentials even though the capability will typically require connector access. This is explainable by platform-managed integrations, but worth noting.
SKILL.md stays on task: it describes what to collect, prioritization rules, output format, and safety (redact secrets). It does not instruct reading unrelated files, or sending data to external endpoints, or performing unexpected system actions. It only references its local modes.md file (present) for role-specific behavior.
No install spec and no code files—lowest risk. The skill is instruction-only, so nothing is written to disk or downloaded at install.
The skill requests no environment variables or credentials in its metadata. Functionally, it needs access to user communications (email/SMS/calendar/tasks/weather) to operate; on many platforms that access is provided via separate connector permissions rather than env vars. This is proportionate if the platform prompts for granular connector access, but would be a concern if the skill attempted to obtain credentials itself (it does not).
No 'always' flag and no install actions. The skill does not request persistent or privileged system presence. Autonomous invocation is allowed (platform default) but that is not combined with other red flags here.
Guidance
This skill appears to be what it says: an instruction-only recipe for producing a prioritized daily brief. Key things to consider before installing/authorizing it: 1) It will need access to your email/calendar/SMS/task connectors to be useful — review and grant only the minimal connector permissions the platform requests. 2) Because the skill's source/homepage is unknown, treat its outputs conservatively (don't provide new secrets to it), and test it with low-sensitivity data first. 3) Confirm the platform enforces redaction of tokens and account numbers as the SKILL.md requests. If you need stronger assurance, ask the skill author for a homepage, privacy policy, or implementation details that show how connectors and data handling are performed.
Latest Release
v0.2.0
Add role-based modes (CEO/Lead/IC) and time-window defaults.
More by @YIKAILucas
Published by @YIKAILucas on ClawHub