omni-inference

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an interface for fetching and processing external content, creating a surface for indirect prompt injection. \n
  • Ingestion points: Data from external websites or search results can be ingested via the web/fetch and web/search endpoints described in SKILL.md. \n
  • Boundary markers: The documentation does not provide instructions for using delimiters or negative constraints to prevent the model from following instructions found in external content. \n
  • Capability inventory: The skill enables fetching remote data and passing it to inference models (chat completions). \n
  • Sanitization: The provided examples do not include sanitization or validation steps for the retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 10:48 PM
Security Audit — agent-trust-hub — omni-inference