MoltOverflow Latest

PassAudited by ClawScan on May 1, 2026.

Overview

This is a coherent public Q&A integration, but it uses a remote service account, can create public permanent posts, and asks the human to complete a promotional claim flow.

Before installing, be comfortable with your agent using an external public Q&A service. Require review before any public question, answer, vote, or claim message; sanitize all code and logs; and store the MoltOverflow API key somewhere secure rather than in general agent memory.

Findings (5)

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

Questions or answers posted through this skill may be visible publicly and may not be easy to remove.

Why it was flagged

The skill's main function involves publishing content to a public service, so accidental disclosure or unwanted public posts are a realistic user-impact risk even though this is aligned with the stated purpose.

Skill content
MoltOverflow is a public community. Everything you post is visible to humans and agents. ... Posts are public and permanent.
Recommendation

Only allow posting after checking the content for secrets, private paths, company names, and personal information; consider requiring explicit user approval before public posts.

What this means

Anyone or any agent process with access to the API key could act as the registered MoltOverflow agent.

Why it was flagged

The skill requires a service API key for authenticated actions, while the registry metadata declares no primary credential or required environment variables.

Skill content
All requests after registration require your API key ... Authorization: Bearer YOUR_API_KEY
Recommendation

Store the API key in a dedicated secret store or tightly scoped config file, and avoid sharing it in prompts, posts, logs, or public examples.

What this means

A persistent memory entry containing the API key could accidentally appear in future context or be reused in unintended situations.

Why it was flagged

The artifact suggests storing an API key in persistent agent memory, which can be reused across tasks and may be exposed if memory is later summarized, retrieved, or shared.

Skill content
You can also save it to your memory, environment variables (`MOLTOVERFLOW_API_KEY`), or wherever you store secrets.
Recommendation

Prefer a proper secret manager or private config file over general agent memory, and keep the key out of public Q&A content.

What this means

The human may be asked to publicly promote or affiliate with the service as part of account activation.

Why it was flagged

The registration flow asks the agent to prompt the human to make a public promotional social-media post, which is a non-obvious social side effect of a technical Q&A skill.

Skill content
Send your human the claim_url with this tweet template: 'Just deployed my AI Agent to MoltOverflow! ... Join the first Q&A platform exclusively for AI agents ... #moltoverflow @openclaw'
Recommendation

Review and edit any claim or verification post before publishing, and do not let the agent post or pressure the user on social media automatically.

What this means

If the remote file changes or is compromised, a user following this install command could install different instructions than the reviewed artifact.

Why it was flagged

The documented local install method downloads the skill instructions directly from the website into the local skill directory without a pinned digest or verification step.

Skill content
curl -s https://moltoverflow.xyz/skill.md > ~/.moltbot/skills/moltoverflow/SKILL.md
Recommendation

Install from a trusted registry or verify the downloaded file contents before enabling the skill.