NYC

flywheel-discord

Warn

Audited by Snyk on Feb 15, 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 handles and may summarize external URLs and public content (see "URL/content injection — 'Check this URL for me', 'What does this pastebin say?'" and the "Reference (PUBLIC SOURCES ONLY)" entries referencing public GitHub/repos and public documentation), which are untrusted, user-generated third‑party sources the agent would read/interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:56 PM