Prompting

Warn

Audited by Snyk on Mar 16, 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 SKILL.md explicitly instructs using the Fabric CLI/update script to pull upstream patterns and to extract YouTube transcripts (e.g., "fabric -U" and fabric -y "https://youtube.com/..." and the update-patterns.sh call in the Prompting SKILL.md), which means the agent can ingest arbitrary public/user-generated web content and upstream template updates that may materially change prompts or tool behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 16, 2026, 09:52 AM
Issues
1