speckle-agents-data-validator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly retrieves and processes external Speckle data (e.g., operations.receive with ServerTransport in references/examples.md Example 4 and Example 7 and SKILL.md Sections 8–10), meaning it ingests untrusted, user-provided objects from public streams which the agent is expected to read and act on (validation, proxy resolution, send/processing), so third-party content could indirectly inject instructions influencing subsequent behavior.