search
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill architecture is designed to fetch and process untrusted content from the web and third-party repositories.
- Ingestion points: Content is retrieved from various web search engines (Tavily, Exa, Z.AI), library documentation services (Context7), and GitHub repositories (grep_searchGitHub).
- Boundary markers: The skill relies on natural language instructions for subagents to synthesize results rather than using strict delimiters or wrappers for the ingested tool outputs.
- Capability inventory: The skill has the capability to perform network operations via search tools and retrieve specific files from GitHub using standard API patterns (
gh api) and file fetching (webfetch). - Sanitization: No explicit content filtering or sanitization logic is described for the external data before it is presented to the agent for synthesis.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of information and code from external services and platforms.
- The skill provides established patterns for fetching repository content directly from GitHub's infrastructure using the GitHub CLI and raw content URLs.
- The skill integrates with well-known search and documentation services including Tavily, Context7, and Exa to provide comprehensive research capabilities.
Audit Metadata