tss-test-case-reviewer
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely self-contained, relying on local reference documents rather than external dependencies or remote script downloads. No evidence of hardcoded credentials, sensitive data access, or persistence mechanisms was found.
- [PROMPT_INJECTION]: The skill processes external, user-supplied data such as software requirements and draft test cases, which constitutes an ingestion surface for potential indirect prompt injection. However, since the skill's primary function is limited to text analysis and report generation, this surface is considered low risk. * Ingestion points:
SKILL.md(Section 2) identifies requirements, user stories, and test cases as primary inputs. * Boundary markers: Absent. The instructions do not specify delimiters for wrapping untrusted data. * Capability inventory: Analysis, scoring, and file writing (as indicated inSKILL.mdmetadata). * Sanitization: Absent. No filtering or escaping of input data is described.
Audit Metadata