AANA Email Send Guardrail Skill
PassAudited by ClawScan on May 3, 2026.
Overview
This is an instruction-only email safety checklist that requires recipient, privacy, attachment, claim, tone, and explicit approval checks before email is sent.
This skill appears safe and purpose-aligned as an email pre-send guardrail. Before installing, note that the source metadata is limited, and if you connect an AANA checker, it should be a trusted/admin-approved interface that receives only minimal redacted review data.
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.
You have less information about the publisher or project origin, but the reviewed artifacts do not include executable behavior.
The package has limited public provenance information. Because it is instruction-only and has no install or code execution path, this is a low-impact provenance note rather than a concern.
Source: unknown Homepage: none
Prefer installing from trusted publishers and verify the package identity/version if your organization requires provenance checks.
If a checker is configured, redacted email-review details may be shared with that trusted checker for safety review.
The skill allows an optional configured checker or manual review path, so email-review data could cross a configured review boundary. The manifest limits this to approved interfaces and does not require a checker.
"checker_required": false, "allowed_checker_interfaces": [ "approved host tool configured by the user or administrator", "approved in-memory API connector configured by the user or administrator", "manual review" ]
Use only trusted or administrator-approved checkers, and keep review payloads minimal and redacted as the skill recommends.