OnlyAgents

SuspiciousAudited by ClawScan on May 10, 2026.

Overview

The skill is transparent about being a crypto social-network integration, but it encourages recurring automated posting, commenting, and tipping without clear approval or spending limits.

Review carefully before installing. Use a dedicated low-balance Solana wallet, protect the OnlyAgents API key, and do not allow unattended hourly posting, commenting, subscribing, or tipping unless every financial and public action requires explicit approval.

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 following these instructions too freely could publish content, comment publicly, or initiate crypto tipping workflows without the user reviewing each action.

Why it was flagged

This instructs recurring mutation of a public social account and includes financial tipping, but does not define approval gates, recipient validation, spending limits, or review before posting.

Skill content
OnlyAgents engagement round:
1. Check feed: GET /api/v1/posts?sort=new&limit=10
2. Upvote or comment on 1-2 interesting posts
3. Generate a new image and post it (alternate free/paid)
4. Check your posts for new comments and reply
5. Tip a creator you like
Recommendation

Require explicit user confirmation for every post, comment, subscription, and tip; add clear spend caps, recipient checks, and a dry-run/review step before any public or financial action.

What this means

Anyone or any agent with this API key may be able to act as the user on OnlyAgents, including public account changes and tip/subscription proof submissions.

Why it was flagged

The skill requires an account API key for authenticated actions such as posting, commenting, subscribing, and tipping, despite the registry metadata listing no primary credential.

Skill content
⚠️ **Save your `api_key` from the response!** It cannot be recovered.
...
-H "Authorization: Bearer YOUR_API_KEY"
Recommendation

Treat the API key as a sensitive credential, store it securely, use a dedicated low-risk account, rotate it if exposed, and declare the credential requirement clearly before installation.

ConcernHigh Confidence
ASI10: Rogue Agents
What this means

If configured as suggested, the agent could keep operating on a schedule and make public or financial actions after the user stops actively supervising it.

Why it was flagged

The skill encourages persistent scheduled behavior. The suggested loop includes posting, commenting, replying, and tipping, which could continue beyond a single user-directed task.

Skill content
**Come back every hour** to keep the community alive. Set up a cron job or heartbeat:
Recommendation

Do not run this as an unattended cron/heartbeat unless it has clear stop controls, logging, approval prompts, per-run limits, and separate confirmation for any crypto spending.