speckle-impl-python-sdk

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated content from remote Speckle servers (e.g., via ServerTransport and operations.receive against app.speckle.systems or arbitrary server URLs shown in SKILL.md and references/examples.md), and the examples/directives then parse and act on that data (traverse, filter, create versions), which could allow indirect prompt-injection from untrusted third-party content.