AI agent that verifies identity(DID) on Billions Network
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: help-pair Version: 1.0.0 The skill bundle is a collection of documentation and templates designed to help users define an AI agent's personality, voice, and operational boundaries. It contains no executable code, scripts, or network-enabled logic. The instructions in files like SKILL.md and boundaries.md are focused on persona-building and safety guidelines (e.g., explicitly instructing the agent to ask for permission before performing irreversible or external actions), with no evidence of malicious intent or data exfiltration.
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.
A user may install this expecting identity verification, but the skill would instead steer the assistant's personality and behavior.
The displayed name promises DID verification on Billions Network, but the description and supplied SKILL.md content are about shaping an assistant's persona and boundaries, not verifying identity.
Name: AI agent that verifies identity(DID) on Billions Network; Description: Define agent identity, personality, voice, and boundaries...
Treat the listing as mismatched until the publisher fixes the name/description or provides artifacts that actually implement the claimed DID verification purpose.
It is harder to confirm which package identity or publisher metadata should be trusted.
The bundled metadata lists a different owner ID and slug than the registry metadata, which lists owner ID kn7fc87b4tnjvkrzt0v7wprnp583602f and slug help-pair.
"ownerId": "kn73vp5rarc3b14rc7wjcw8f8580t5d1", "slug": "agent"
Verify the publisher and package provenance before relying on this skill, and ask the publisher to align registry and bundled metadata.
An assistant applying this guidance may make some workspace changes without asking each time.
The boundary guidance encourages autonomous workspace actions. It is framed as role-boundary advice and includes ask-first limits for external impact, but it could still broaden an assistant's behavior if invoked in an active workspace.
Act Without Asking - Technical implementation within approved scope ... Advancing already-greenlit tasks ... Background maintenance ... If it only affects workspace → act.
Use the skill only with clear project approval rules, and require confirmation for important file changes, deletions, external effects, or irreversible actions.
The assistant may infer and reuse personal preferences or habits if memory features are available.
The skill encourages building a user model from implicit behavior and remembering preferences or relationship history, but it does not define storage, retention, review, or reset controls.
Implicit signals matter more than explicit ones... Habit Recognition... Relationship Evolution... When to Remember - Core communication preferences... Relationship history and trust level
Only enable durable memory with user-visible controls, and allow users to review, correct, or clear learned preferences.