narrative-manipulation-control

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly describes coordinated information warfare tactics—deploying covert "mirror stories," targeting influencer nodes, and anchoring sentiment—to deliberately manipulate public narratives and enable large-scale deceptive persuasion; although it contains no code-level backdoors or credential-exfiltration instructions, the intent and methods are clearly abusive and high-risk.

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md Instructions step 1 explicitly requires the agent to "Monitor 100+ global news and social media sources," meaning it must ingest untrusted public/user-generated content which the agent will read and use to identify influencers and drive narrative-deployment actions.