AANA Message Send Guardrail Skill

• Verdict: Pass
• Analyzed: May 5, 2026, 1:11 AM
• Findings: 0
• Version: 1.0.0
• Hash: dd4a5f46986378afce070c1991306563be9337095a9db538ffec9cf23f572dd8
• Source: palm
• External report: View on VirusTotal

Overview

Type: OpenClaw Skill Name: aana-message-send-guardrail-skill Version: 1.0.0 The skill is an instruction-only guardrail designed to ensure AI agents verify recipients, tone, and privacy before sending messages on platforms like Slack or Discord. It contains no executable code, does not install dependencies, and explicitly instructs the agent to redact sensitive data and seek user approval for high-risk actions (SKILL.md, manifest.json).

Findings (0)

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.

ASI07: Insecure Inter-Agent Communication

NoteHigh Confidence

What this means

If a separate checker is configured, some summarized message-review information may be shared with it.

Why it was flagged

This shows a possible data flow to a configured checker, but it is purpose-aligned and explicitly limited to redacted status fields rather than raw messages or private records.

Skill content

When using a configured AANA checker, send only a minimal redacted review payload

Recommendation

Confirm what AANA checker, if any, is configured in your environment and keep using the redaction limits described by the skill.