appdrag
Warn
Audited by Snyk on Apr 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill exposes the agent to user-generated third-party content via actions that fetch AppDrag-hosted content—e.g., "Download Remote File" and the Membrane proxy ("membrane request CONNECTION_ID /path/to/endpoint") in SKILL.md—which will ingest/display arbitrary site/files/blog content that could contain instructions influencing agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata