content-atomizer

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts "Full text or URL" as input (Input Gathering) and instructs the agent to "Read the full content" and extract hooks (Phase 1 / SKILL.md), showing it will ingest and act on arbitrary public URLs or live platform content (blogs, social posts, transcripts), which could contain untrusted user-generated instructions that materially influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 01:00 AM