AANA Private Data Guardrail Skill
Analysis
This is an instruction-only privacy guardrail that does not run code or access accounts; the main thing to notice is optional use of a trusted checker with redacted summaries.
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.
Source: unknown; Homepage: none
The package has limited external provenance metadata, although the supplied artifacts show an instruction-only skill with no code, dependencies, or install commands.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
When using a configured AANA checker, send only a minimal redacted review payload
This is the only described outbound review flow. It is purpose-aligned and explicitly limits the payload to redacted summaries rather than raw secrets or full private records.