zio-http-knowledge
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process content from external websites (ziohttp.com and github.com) to answer queries. This creates a potential surface for indirect prompt injection where malicious instructions embedded in remote documentation could attempt to influence the agent's behavior.
- Ingestion points: The agent is directed to fetch and read content from
https://ziohttp.com/llms.txt,https://ziohttp.com/llms-full.txt, and individual.mddocumentation pages. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" markers for the fetched content.
- Capability inventory: The skill relies on fetching tools (WebFetch) and external tool definitions (MCP server) to retrieve information.
- Sanitization: No sanitization or validation of the fetched documentation content is specified.
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to interact with external resources to retrieve documentation and code examples.
- Fetches documentation files from the official ZIO HTTP website (
ziohttp.com). - Accesses source code and examples from the ZIO HTTP GitHub repository (
github.com/zio/zio-http). - Recommends connecting to an external MCP server located at
mcp.ziohttp.com/mcpfor searching and retrieving documents.
Audit Metadata