ipfs

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching content from public IPFS gateways (e.g., "https://ipfs.io/ipfs/") and shows workflows that use ipfs cat/get and loop over arbitrary CIDs, which means the agent would ingest and act on untrusted, user-generated content from the public IPFS network.