effect-ai
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines an interface for processing untrusted data through AI completions and tool handlers, presenting an indirect prompt injection surface. 1. Ingestion points: External data is ingested through the AiChat.generateText and generateObject methods in SKILL.md. 2. Boundary markers: The framework utilizes effect/Schema for structural validation of tool inputs and AI responses. 3. Capability inventory: Examples reference capabilities for web searching and mathematical expression evaluation in SKILL.md. 4. Sanitization: Inputs and outputs are constrained by schema validation, though the library relies on underlying LLM guardrails for instruction-level sanitization.
- [CREDENTIALS_UNSAFE]: The skill demonstrates secure credential management by using the Config.redacted pattern for API keys in code examples.
- [EXTERNAL_DOWNLOADS]: The documentation references installation of legitimate libraries from the @effect organization on the public NPM registry.
Audit Metadata