tanstack-start-testing
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze external, potentially untrusted data to diagnose issues.
- Ingestion points: The skill processes changed application behavior, browser console logs, and network output to reproduce failures (SKILL.md).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when handling external diagnostic content.
- Capability inventory: The skill refers to executing production builds, linting, and type-checking, which typically involves shell command execution (SKILL.md).
- Sanitization: Absent. There are no instructions provided to sanitize or validate the content of analyzed logs or source code changes before processing.
Audit Metadata