react-flow-architect
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a
GraphAnalyzerutility that processes potentially untrusted file content, establishing a theoretical surface for indirect prompt injection. - Ingestion points: The
analyzeCode(content, filePath)method inSKILL.mdingests raw strings for analysis. - Boundary markers: Absent; there are no delimiters or "ignore" instructions for the processed content.
- Capability inventory: The script is limited to metric calculation via static Regex patterns and logic-based issue detection. No dangerous capabilities such as file system modifications, network requests, or command execution are present within this analyzer utility.
- Sanitization: Input content is processed directly without filtering.
Audit Metadata