viral-short-form

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill is a benign short-form content guide but includes an instruction to "strip competitor watermarks (re-export clean)," which encourages evasion of platform provenance rules and is suspicious without clear malicious intent.

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow only uses outsider-authored free text from the end-user brief/draft (e.g., the prompt “Give me hooks…” / “Here’s my script. Where does it lose people?”) as input for generation/critique, without reading any third-party feed/queue content directly.