pattern-of-life-from-socials

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content is high-risk: it gives operational, actionable tradecraft for intrusive surveillance, geolocation and deanonymisation of individuals (including evasion techniques) that can be used for stalking, doxxing or other abusive targeting.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow reads and records free-text content from outsider-authored social posts/comments/metadata by fetching a user’s public profile and each post (“Post URL… Text verbatim”, “Archive the profile and every post…”, “Read past the subject of each photo…”), so an outsider can submit poison via posting or comments that the workflow ingests without selecting a specific trusted item first.