fit-scorer

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow for “Score/Compare influencers” necessarily requires ingesting influencer-provided or publicly available profile/content/engagement text (e.g., captions, comments, bios) to justify scores, which is outsider-authored free text read into the agent’s LLM context via whatever data-fetching/API/scraping step retrieves that content.