humanizer

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's workflow (SKILL.md and README usage examples like "/humanizer [paste your text here]" and "Please humanize this text: [your text]") explicitly ingests arbitrary user-provided text at runtime, so untrusted third-party content could be supplied and potentially contain embedded instructions that influence the agent's output (indirect prompt injection).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 09:35 PM