tanstack-start-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands such as
ls,grep,rg(ripgrep),find, andtestto perform project auditing and architecture validation. These commands are restricted to the local file system and are used to verify the presence of specific files, search for patterns in code (like secret exposure), and check project configuration. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data by reading local project source files,
package.json, and configuration files. While it lacks explicit boundary markers to delimit this external data when processed by the agent, its capabilities are scoped to local file system analysis and providing architectural guidance, which is consistent with its primary purpose as a developer tool. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes defensive patterns to prevent data exposure in the target project. It specifically instructs the agent to check for hardcoded secrets and environment variable leaks (e.g., searching for
VITE_SECRET,PASSWORD, etc.) to ensure they are not included in client-reachable code. No evidence was found of the skill itself exfiltrating data or hardcoding credentials.
Audit Metadata