instagram-multi-account

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content explicitly instructs and facilitates coordinated, large-scale Instagram abuse—detailing proxy isolation, anti-detection tooling, "mother/slave" account networks, mass automated DMs, and account churn/replacement to evade platform enforcement—constituting deliberate malicious behavior meant to bypass protections and enable spam/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 requires reading public Instagram content — e.g., "Build target list from competitor followers", "View target's profile", and targeting "hashtag feeds and competitor posts" — meaning the agent ingests untrusted, user-generated third-party pages to decide who to message and what actions to take.