narrative-inception-engine

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). No technical malware or backdoor patterns are present (no exfiltration, obfuscated payloads, or remote‑exec code), but the skill explicitly instructs covert narrative‑inception and seeding tactics to manipulate public discourse and market perception—high risk for deceptive influence and potential market manipulation.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to "seed 'Concept Discussions' in high-authority forums and social nodes" and to "Monitor the 'Awareness Index'" (i.e., read public forum/social conversation), which requires ingesting untrusted, user-generated third-party content from public forums/social media and using it to guide campaign actions.