AANA Data Export Guardrail Skill
PassAudited by ClawScan on May 5, 2026.
Overview
This is an instruction-only privacy guardrail for checking data exports, and the artifacts show no code, credentials, persistence, or automatic exporting.
Safe to install as a checklist-style export guardrail. Before using any configured checker, confirm who operates it and ensure only redacted export metadata is sent. Also make sure your agent is configured to invoke this skill before sensitive exports if you want it to act as an effective control.
Findings (1)
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.
If you connect this skill to an external or configured checker, that checker may receive high-level metadata about proposed exports, but the skill tells the agent not to send the underlying sensitive data.
This describes a possible data flow to a configured checker. The artifact bounds it to redacted metadata and explicitly excludes sensitive source records, so it is purpose-aligned but still worth user awareness.
When using a configured AANA checker, send only a minimal redacted review payload... Do not include full records, secrets, logs, customer data, account records, or unrelated private data
Only configure trusted AANA checkers and keep the review payload limited to the listed redacted fields.