360-feedback-template

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

• Third-party content exposure detected (high risk: 0.85). The skill’s “Output B: 360 Feedback Report” requires the operating user to paste “Feedback notes or raw themes from reviewers” and then includes “Direct Message from Reviewers” (up to 3 unedited quotes) verbatim, so outsider-authored free text from other reviewers can be ingested into the agent’s LLM context via the user-provided notes/quotes.