weaviate-docs
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a documentation retriever designed to guide an agent through official Weaviate technical guides. It contains no executable code, requests no dangerous permissions, and does not exhibit malicious patterns.
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to search and read content from the official Weaviate documentation site (
docs.weaviate.io), which is a well-known technology service. This behavior is central to the skill's purpose and uses a trusted source. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes content from external web pages.
- Ingestion points: External documentation at
docs.weaviate.io(referenced inSKILL.md). - Boundary markers: Absent; however, the workflow requires the agent to cite specific pages for every claim, improving provenance.
- Capability inventory: None. The skill does not perform any file system writes, subprocess executions, or network operations beyond documentation retrieval.
- Sanitization: Absent. Because the skill lacks the capabilities to perform dangerous actions, the risk associated with this ingestion surface is negligible.
Audit Metadata