effect-ai-language-model
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill documents interfaces for ingesting external data into LLM prompts, which represents a structural attack surface for indirect prompt injection. Ingestion points: prompt parameters in generateText, generateObject, and streamText (SKILL.md). Boundary markers: The skill highlights the use of Schema for validating model output but does not define specific input delimiters. Capability inventory: Documentation includes patterns for tool calling and toolkit execution. Sanitization: Promotes the use of effect/Schema to ensure type safety and validation of responses.
Audit Metadata