qa-robot-framework-writer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external test case specifications and requirements to generate executable Robot Framework code. This creation of executable logic based on untrusted data creates a potential surface for indirect prompt injection. \n
- Ingestion points: The workflow involves reading test cases from specs, requirements, and manual test designs (SKILL.md). \n
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the test case documents. \n
- Capability inventory: The skill generates scripts utilizing network operations (RequestsLibrary) and browser automation (SeleniumLibrary/BrowserLibrary), providing a significant impact surface if successfully injected. \n
- Sanitization: The skill lacks defined validation or sanitization steps for input data content. \n- [EXTERNAL_DOWNLOADS]: The documentation references the installation of standard, well-known Robot Framework libraries and parallel execution tools via the pip package manager. \n- [COMMAND_EXECUTION]: The skill provides numerous examples of shell commands for installing dependencies and executing Robot Framework test suites in various environments.
Audit Metadata