reference-sdk

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill facilitates the ingestion of external data from SDK repositories which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: External codebases queried via the btca ask command.
  • Boundary markers: None specified in the instructions to prevent the agent from obeying instructions found within the retrieved code.
  • Capability inventory: The agent is instructed to interact with a shell environment to run the btca tool.
  • Sanitization: No sanitization of the retrieved content is mentioned before it is processed by the agent.
  • [Command Execution] (SAFE): The skill provides examples of using a command-line tool (btca). These are standard usage patterns for a developer tool and do not involve suspicious parameters, shell piping to interpreters, or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:02 PM