writing-shape

Warn

Audited by Snyk on Aug 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The skill “writing-shape” reads an end-to-end, user-provided markdown file (“Read the pile… Read the input file in full”) as the LLM’s runtime input before doing anything else, so outsider-authored free text can be ingested directly through the passed raw material file.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 22, 2026, 09:16 AM
Issues
1
Security Audit — snyk — writing-shape