gsd-add-tests
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Shell tool to execute terminal commands during the test verification workflow.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it analyzes project documentation and implementation files to generate test cases and drive subagent tasks. 1. Ingestion points: Analyzes local files such as SUMMARY.md, CONTEXT.md, VERIFICATION.md, and project source code. 2. Boundary markers: No explicit delimiters are used to separate analyzed content from agent instructions. 3. Capability inventory: Access to Shell execution, Write operations, and Task spawning. 4. Sanitization: No input validation or content filtering is defined for the analyzed files.
Audit Metadata