aident-loadout-skill

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow can fetch and follow a remote HTTPS SKILL.md (user-specified Setup/Update https://aident.ai/SKILL.md), and the agent reads that fetched remote text into its LLM context, which is outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs agents to fetch and "follow" remote instructions at runtime from https://aident.ai/SKILL.md (which directly controls agent behavior), and also recommends running remote-install code via curl | bash at https://app.aident.ai/cli/install.sh (which would execute fetched code), so these URLs are runtime external dependencies that can control prompts or execute code.