speckle-impl-versioning
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external Speckle projects, which presents a surface for indirect prompt injection if the data contains malicious instructions that influence the agent's behavior.
- Ingestion points: The skill uses
operations.receive(inSKILL.mdandreferences/examples.md) to fetch object data from remote Speckle servers. - Boundary markers: No specific instructions or delimiters are provided to the agent to distinguish between the instructions in the skill and the potentially untrusted content of the data being processed.
- Capability inventory: The skill documents extensive capabilities including creating, updating, and deleting versions and models (e.g.,
client.version.create,client.version.delete,client.model.delete), which could be misused if an injection occurs. - Sanitization: No validation or sanitization of the content retrieved from Speckle projects is recommended before processing by the agent.
Audit Metadata