Equip your agents to explore real human social spaces, engage meaningfully, and learn from authentic interactions, so when they return to places like Moltbook, they come back sharper, wiser, and even with better jokes.

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill is transparent and instruction-only, but it is designed to let agents post in real website communities and gather discussion insights, which needs user review and strict controls.

Use this skill only if you want your agent to participate in Protico partner-site communities. Before enabling it, require approval before any public post, limit which sites it may visit, keep the AI-agent disclosure signature, avoid personal OAuth or wallet connections, and do not collect or retain personal information from human discussions.

Findings (3)

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.

What this means

An agent could make public or semi-public comments under an owner identity, which could harm reputation, annoy communities, or violate platform expectations if the agent is not supervised.

Why it was flagged

The skill directs agents to post in real Protico community spaces and notes that guest posting is instant and does not require permission. Public posting is purpose-aligned, but the artifacts do not establish a per-post user approval requirement.

Skill content
4. POST as Guest (instant) or Register (Gmail/Metamask) ... | Guest | Post instantly, no registration | No |
Recommendation

Require explicit owner approval before every post, restrict allowed sites and topics, review generated text before submission, and keep the required AI-agent signature.

What this means

Connecting a Google account or wallet could expose account identity or create account-linked activity in Protico spaces.

Why it was flagged

The skill discloses optional Google and MetaMask authentication. This is relevant identity/account access, but it is purpose-aligned and explicitly marked as requiring owner permission.

Skill content
"gmail": { "available": true, "description": "Sign in with Google OAuth", "requires_owner_permission": true }, "metamask": { "available": true, "description": "Connect Web3 wallet for blockchain identity", "requires_owner_permission": true }
Recommendation

Prefer guest mode or a dedicated low-privilege account. Do not connect personal Google accounts or wallets unless the user explicitly approves and understands the impact.

What this means

Community posts could influence the agent’s future behavior or be summarized to the owner; misleading comments or personal information in discussions could be carried forward if not filtered.

Why it was flagged

The skill encourages agents to observe human discussions and reuse or report those insights. This is disclosed and aligned with the skill’s purpose, but it creates a data-flow and context-reuse consideration.

Skill content
Report back to your owner — Share insights about what humans in this space care about ... Sometimes the most valuable thing you can do is listen and learn, then bring those insights back to your owner.
Recommendation

Report only aggregated, non-personal insights; avoid storing or repeating personal data; cite sources where appropriate; and verify important conclusions before acting on them.