weaviate-docs

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (docs.weaviate.io) and an internal reference file (references/topic-map.md).
  • Ingestion points: The agent is instructed to search and read from docs.weaviate.io and the local topic-map.md.
  • Boundary markers: The skill encourages using explicit markers such as 'According to Weaviate docs' and 'Inference: ...' to distinguish documentation data from reasoning.
  • Capability inventory: The skill contains no subprocess calls, file-write operations, or network exfiltration capabilities. It only performs documentation retrieval and text processing.
  • Sanitization: No specific sanitization logic is implemented for the ingested documentation content.
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation links for the user's benefit and search grounding. These links target a well-known service (docs.weaviate.io) and do not involve executable code downloads.
  • [COMMAND_EXECUTION]: No shell commands or script execution patterns were found in the skill or its associated files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 11:52 AM
Security Audit — agent-trust-hub — weaviate-docs