seed-hypermedia-read

Warn

Audited by Snyk on Feb 27, 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 workflow explicitly fetches documents and comments via Seed gRPC and instructs the agent to "Download media referenced by IPFS" (via the local HTTP gateway), meaning the agent will ingest untrusted, user-generated content from IPFS/Seed responses and use extracted fields to drive subsequent RPCs, creating a path for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 04:12 PM