test-case-generator
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external platforms and project files, which represents an indirect prompt injection surface where malicious content in those sources could influence agent behavior.\n
- Ingestion points: Context is gathered from Jira, Confluence, Figma, Miro, and project source code files during the initial workflow step (SKILL.md).\n
- Boundary markers: The agent is instructed to present a list of sources for user approval (Step 1.1) and a generated checklist (Step 3.1) before creating the final test cases.\n
- Capability inventory: The skill is authorized to scan the project directory for source code and create new markdown files containing test cases (SKILL.md).\n
- Sanitization: The skill does not explicitly describe methods for filtering or sanitizing instructions found within external documents or code comments.
Audit Metadata