first-aid-kit
Analysis
This instruction-only first-aid learning skill is coherent and has no code or credential access, but users should notice the optional daily-tip scheduler and its safety-notice exception.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
When the user asks to enable daily tips, call `cron.add` to create a recurring isolated job ... "schedule": { "kind": "cron", "expr": "0 9 * * *" } ... "delivery": { "mode": "announce" }This creates a persistent scheduled agent action. It is disclosed, user-triggered, isolated, and limited to one daily educational tip, so it is a notice item rather than a concern.
Safety Notice (always prepend to every response) ... No safety notice needed.
The skill globally says every response should include an emergency safety notice, but the daily-tip payload explicitly omits it. In a first-aid context, inconsistent safety framing is worth noticing even though the daily tips are educational.
