speckle-impl-tekla

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

• Third-party content exposure detected (high risk: 0.80). The skill's examples and methods (references/examples.md Example 2 and references/methods.md) explicitly show using SpecklePy to authenticate to a Speckle server and receive commits/streams (operations.receive) from remote Speckle projects, which means the agent ingests and acts on potentially untrusted, user-generated third-party model data from external servers.