locoagent-social-media-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for this skill uses agent-browser to open and snapshot live web pages (e.g., X.com timelines/search results) and then feeds the extracted page text/DOM content into the agent’s LLM loop for decision-making, which is outsider-authored free text from public web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's installation/setup fetches and executes remote code: the installer curl https://bun.sh/install | bash executes a remote script during setup, and git clone https://github.com/LocoreMind/locoagent.git pulls repository code that the agent runs—both are required external dependencies that can execute or control runtime behavior.