anthropic-streaming-patterns
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains standard implementation patterns for the Anthropic SDK. No malicious code, obfuscation, or unauthorized network operations were found.- [SAFE]: Analysis of the indirect prompt injection surface identifies that the skill handles tool parameters from the API stream through JSON parsing. While this creates a data ingestion point, it is handled according to standard SDK event patterns for tool execution (contentBlockDelta and contentBlockStop) and is inherent to the intended functionality.
Audit Metadata