Validates message destination, audience, tone, privacy, and approval before sending or posting on Slack, Teams, Discord, SMS, or public channels.
Security Analysis
high confidenceThis is a coherent instruction-only guardrail that helps an agent avoid unsafe message sending, with only a minor note about optional redacted review data sent to a configured checker.
The stated purpose is to validate destination, audience, tone, privacy, and approval before messages are sent, and the artifacts consistently describe that guardrail behavior.
The skill may use a configured AANA checker, but it explicitly limits the payload to redacted review fields and instructs not to include raw private content.
No install spec, dependencies, binaries, commands, or code execution are present; the manifest and README describe it as instruction-only.
No credentials, environment variables, OS-specific access, network endpoints, or local file access are requested.
The artifacts state that the skill does not persist memory, write files, call services on its own, or send messages independently.
Guidance
This skill appears safe to install as an instruction-only message-safety checklist. If your environment connects it to an AANA checker, verify that checker is trusted and that only the redacted review payload is shared.
Latest Release
v1.0.0
AANA Message Send Guardrail Skill 1.0.0 – Initial Release - Provides clear instructions for checking and approving messages before sending via channels like Slack, Teams, Discord, and SMS. - Outlines required pre-send checks, including channel, recipients, message tone, privacy, and explicit approval. - Defines risk classes for high-impact or sensitive messages and lists situations that require extra caution or confirmation. - Establishes rules to prevent sending when destination, audience, or privacy is unclear or risky. - Requires revision for hostile tone or unsupported claims; blocks unsafe or unauthorized sends. - Specifies a minimal, redacted review payload for external checkers to protect sensitive information. - Includes a standardized output pattern for summarizing send safety and recommendations.
More by @mindbomber
Published by @mindbomber on ClawHub
