ork-explore
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes codebase files and external documentation, which serves as an ingestion point for untrusted data that could contain malicious instructions.
- Ingestion points: Reads local source code files and queries third-party documentation via the
context7MCP server (found inSKILL.md). - Boundary markers: None specified; the skill lacks explicit delimiters or instructions to ignore embedded commands within the files it processes.
- Capability inventory: The skill utilizes the
context7MCP server (resolve-library-id,query-docs) and relies on codebase exploration tools likeork_explorer(found inSKILL.md). - Sanitization: There are no mechanisms described for sanitizing or validating the content of the files or documentation retrieved before processing.
Audit Metadata