Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill's setup and update steps run unpinned third-party npm packages (`claude-flow@alpha`, `flow-nexus@latest`, `whatsapp-mcp`) and auto-update them globally, which is a risky supply-chain exposure, but nothing shows intent to attack the user.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required health-check routine runs `mcp__whatsapp__list_chats`, which returns chat listings and message content from WhatsApp contacts, and anyone who can message the user can place text into that feed without the agent selecting a specific item.
kmondlane/ExoMind
8794d26
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.