test-case-ideation-from-story
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely focused on text-to-text transformation for the purpose of test case ideation. It does not include any executable scripts, shell commands, or requests for sensitive permissions.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is designed to process untrusted data (user stories and feature specs).
- Ingestion points: The skill ingests user stories, acceptance criteria, and mockup notes from external project documentation (e.g.,
docs/SRCH-88.md). - Boundary markers: The instructions do not define delimiters or specific "ignore" instructions for the input data, though it uses a structured extraction process in Step 1.
- Capability inventory: The skill's capabilities are limited to emitting Markdown text. It has no tool-based access to the network, file system, or subprocesses.
- Sanitization: There is no explicit sanitization of input data before it is processed into the output matrix.
- [EXTERNAL_DOWNLOADS]: The skill references several external resources for documentation and educational purposes, such as ISTQB, Cucumber, and TestRail. These are well-known services and industry-standard reference sites, and the links are used neutrally to support the skill's primary function.
Audit Metadata