scientific-critical-thinking

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md workflow explicitly requires checking external pre-registration records (ClinicalTrials.gov, PROSPERO, OSF) and comparing registered outcomes to reported results, so the agent would fetch and interpret public, user-submitted third-party content that can directly affect its appraisal and next actions.