prd-auto-test-loop
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to manage the local file system, specifically for creating version-specific test directories (
mkdir -p) and initializing Markdown templates (cat). These operations are used to set up the testing environment. - [DYNAMIC_EXECUTION]: The skill employs an automated self-test loop where it generates, runs, and iteratively fixes Unit, Integration, and E2E test scripts. This involves runtime execution of code that the agent generates or modifies based on its own analysis of test failures.
- [INDIRECT_PROMPT_INJECTION]: The skill's logic is driven by the content of external PRD files, creating a surface for indirect instructions.
- Ingestion points: Product Requirement Documents (PRDs) provided as input or read from the file system within the
SKILL.mdworkflow. - Boundary markers: No specific delimiters or safety instructions are defined to separate the external data (PRD content) from the agent's internal code-generation logic.
- Capability inventory: The agent can write to the file system, create directories, and execute shell commands/test suites as part of the 'AI self-test loop'.
- Sanitization: The skill lacks explicit sanitization or validation mechanisms for the PRD content before incorporating it into the automated test generation and execution cycle.
Audit Metadata