zio-blocks-knowledge
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates access to official ZIO Blocks documentation via established project domains and tools. All external resources, including the documentation website (zioblocks.com), the MCP server (mcp.zioblocks.com), and the source code repository (github.com/zio/zio-blocks), are official channels for the library and its development. The retrieval of documentation strings for internal library knowledge is a standard functional requirement for this type of skill.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion surface by instructing the agent to fetch and process external documentation content which could be modified at the source.
- Ingestion points: External documentation URLs such as https://zioblocks.com/llms.txt, https://zioblocks.com/llms-full.txt, and individual Markdown documentation pages (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when it interpolates fetched content into its context.
- Capability inventory: The agent uses retrieved information to generate natural language responses and code snippets for the user.
- Sanitization: No explicit sanitization or filtering of the external documentation content is performed.
Audit Metadata