sparc-methodology

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow described in SKILL.md includes a researcher mode that performs parallel “WebSearch/WebFetch” (and other modes that can analyze/code), which indicates it may ingest outsider-authored free text from the web based on attacker-controlled task prompts or chosen sources.