test-design
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository instructions, interfaces, and implementation files to establish expected behavior (SKILL.md, Workflow step 1; references/test-selection.md). No explicit boundary markers or delimiters are used to isolate this external content from the agent's instructions. The skill has capabilities to modify files and execute shell commands (SKILL.md, Workflow step 4). No specific sanitization or validation of the external content is described before it is processed for test design.\n- [COMMAND_EXECUTION]: The workflow includes the execution of shell commands to run and verify tests. This behavior is restricted to the repository's existing testing tools and conventions as established during the inspection phase.\n- [SAFE]: No malicious code, exfiltration patterns, or obfuscation techniques were detected in the skill instructions or reference materials.
Audit Metadata