policy-influence-simulation

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High risk: the skill explicitly instructs targeted profiling of policymakers, tailoring messaging to cognitive biases, designing "grassroots" digital campaigns (astroturfing), and strategizing to influence or evade regulation for corporate benefit—clear indicators of deliberate deceptive political manipulation and regulatory circumvention.

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 requires "Analyze public positions of 50+ key policymakers," which obliges the agent to ingest and interpret untrusted public third‑party content (public statements/posts/web coverage) that can materially influence simulations and follow‑on actions.