google-ai-mode-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external API and interpolates it into the agent context. * Ingestion points: The skill processes user search queries and returns text_blocks and references from the Scavio API (SKILL.md). * Boundary markers: No explicit delimiters are specified to isolate external content. * Capability inventory: The skill performs network requests and processes JSON responses using the requests library. * Sanitization: No response sanitization or filtering is described.
  • [DATA_EXFILTRATION]: The skill transmits search queries to a remote endpoint. * Evidence: Requests are made to https://api.scavio.dev/api/v2/google/ai-mode. * Context: The endpoint belongs to the vendor's documented infrastructure.
  • [EXTERNAL_DOWNLOADS]: The skill relies on external Python libraries. * Evidence: The example code utilizes the requests package.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:24 PM
Security Audit — agent-trust-hub — google-ai-mode-api