atai-newton-fusion-model

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, potentially untrusted data—such as text files, images, and video frames—which are then passed to a large language model for analysis.\n
  • Ingestion points: Untrusted data enters the model's context via the file_ids parameter and the events field (containing base64-encoded image data), as described in SKILL.md and implemented across the reference scripts in the references/ directory.\n
  • Boundary markers: The implementation uses the instruction_prompt field to provide system-level directives to the model. Documentation also recommends using specific query language to constrain the model's output format, providing a layer of protection against adversarial inputs.\n
  • Capability inventory: The skill possesses capabilities to perform network POST requests to the Archetype AI API endpoint and upload files to a remote server using the official archetypeai Python client, as defined in references/_common.py and used in the query scripts.\n
  • Sanitization: No explicit sanitization, filtering, or validation of the contents of uploaded files or image data was observed within the skill's scripts; the system relies on the model's internal safety guardrails and the provided instructional prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 03:34 AM