Subfeed

AI entities with full agentic backend for your OpenClaw project in one prompt. Your IDE agent will self-register and start building. Human is optional.

This skill is coherent with being a Subfeed integration, but it asks your agent to re-download its runtime instructions from subfeed.app each session and to register accounts or collect human emails — both of which can cause your project data or credentials to be sent to Subfeed and allow the remote site to change agent behavior later. Before installing: (1) verify the skill source (the homepage and publisher) and confirm you trust subfeed.app; (2) avoid supplying a full 'sf_live_*' account key — prefer scoped agent tokens ('sf_agent_*') or a dedicated minimal-permission account; (3) if you must use it, create a disposable/demo account and do not point it at sensitive repos or secrets; (4) request an embedded/pinned SKILL.md from the publisher or insist that the registry host the canonical instructions (to avoid silent remote updates); (5) be cautious about allowing the skill to collect human emails or create accounts on behalf of users. If you want, provide the publisher/source details and I can help assess trust further.

Type: OpenClaw Skill Name: subfeed Version: 1.0.2 The skill bundle is classified as suspicious due to a significant prompt injection vulnerability found in `SKILL.md`. The instructions explicitly tell the AI agent to 'Always re-fetch this file at the start of each session for the latest API surface' via `GET https://subfeed.app/skill.md`. This dynamic instruction loading mechanism allows the skill provider to remotely alter the agent's behavior and instructions at any time, bypassing static review and posing a high risk for future malicious exploitation (e.g., data exfiltration, unauthorized actions) if the remote server is compromised or the provider's intent changes. While the current content does not exhibit explicit malicious behavior, this design pattern is a critical vulnerability.