corporate-misalignment-finder

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow ingests the user-provided “misalignment situation” input (e.g., meeting transcript/decision log/complaint), which can include outsider-authored free text (e.g., transcripts or comments written by others) that the agent then processes and places into the LLM context.