validate-tests
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it processes untrusted test code and feature descriptions.
- Ingestion points: Test code and feature artifacts are ingested from user input.
- Boundary markers: Absent. No markers are used to delimit external data.
- Capability inventory: The skill uses vendor tools (mcp__helpmetest-*). No arbitrary command execution or file-system writes are defined in the markdown.
- Sanitization: Absent. The skill does not sanitize or validate external input before processing.
Audit Metadata