The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external source code to generate test cases. This creates an attack surface where malicious instructions embedded in the source code (e.g., in comments) could influence the agent's behavior during the generation process.
Ingestion points: Source files and directories specified via the --file and --scope flags in the aqe CLI, as described in SKILL.md.
Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded within the analyzed source code.
Capability inventory: The skill has the capability to write files to the local filesystem, specifically into the tests/ directory as configured in config.json.
Sanitization: Absent. There is no mention of sanitizing, escaping, or validating the content extracted from source files before it is processed by the AI models.
[DYNAMIC_EXECUTION]: The skill uses code analysis and predefined templates to generate executable test scripts for various frameworks like Jest and Vitest.
Evidence: The agent workflow in SKILL.md explicitly instructs the generation of test code (e.g., Output to tests/unit/services/PaymentService.test.ts) using templates defined in templates/test-scaffold-jest.md.

qe-test-generation