cloudfiles

Warn

Audited by Snyk on Apr 26, 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.md explicitly shows the agent making API/proxy requests to CloudFiles and handling "File Content" and "File Metadata" (see the "Proxy requests" and "File" sections and the membrane request examples), which means the agent will fetch and read user-provided third-party content that could influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 26, 2026, 09:17 PM
Issues
1