create-asb-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 for the published asb-* skill includes asking for and reading the end user’s pasted/input free text (e.g., the “user pastes text” artifact to audit), which is outsider-authored relative to the developer who produced the skill, and that pasted prose is fed into the LLM context.