ds-plan

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow reads and ingests outsider-authored free text from external plugin skill reference/example READMEs during Step 5b External Skill Discovery (it explicitly instructs Glob skills/X/examples/** and then “Read … README.md … in full”), which can contain arbitrary prose authored by parties other than the operating user and is then placed into the agent’s LLM context for planning decisions.