mmk-plaud

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

• Third-party content exposure detected (high risk: 0.85). The skill is a CLI wrapper over an unofficial Plaud web API; at runtime it will fetch outsider-authored free text such as Plaud recording transcripts/summaries (from Plaud’s servers) and inject that returned prose into the agent’s LLM context via the sub-commands like mmk-plaud-file/mmk-plaud-search when composing results.