global-soft-power-lobbying

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.95). This skill outlines a deliberate, covert influence operation—privacy-invasive “deep research” into private motivations, bespoke briefs framed as the “only logical solution,” stealthy micro-targeting to individual decision‑makers and their inner circles, and ongoing behavioral monitoring—enabling targeted manipulation of institutional actors and likely privacy/ethical abuses.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly requires "Deep Research" to analyze decision‑makers' public and private motivations and to "monitor" targets' public statements, which entails ingesting and interpreting open/public third‑party content (e.g., media articles, social posts) that could carry untrusted instructions.