instagram-superpower

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content contains deliberate instructions and tooling to obtain, store, transfer and reuse Instagram credentials/cookies (including purchased accounts and automated browser login + TOTP), enabling credential exfiltration and account takeover.

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

• Third-party content exposure detected (high risk: 0.75). scripts/download.sh runs Groq/local transcription and then prints the resulting transcript text (CHUNK_TEXT / TRANSCRIPT) to stdout, which is then available to the agent/LLM for subsequent analysis; this transcript is derived from outsider-authored Instagram media content.