miro-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documentation and code samples align with the stated purpose of managing Miro connectors and items. It uses standard Node.js modules and API fetch patterns without any detected malicious intent or obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests data from the Miro API and possesses write capabilities back to the platform.
- Ingestion points: API responses from
api.miro.comprocessed viamiroFetchinSKILL.md. - Boundary markers: None identified in the provided code snippets or instructions.
- Capability inventory: Network requests via
miroFetchand local file reading viafs.readFileSyncinSKILL.md. - Sanitization: No explicit sanitization or validation of API responses is demonstrated.
Audit Metadata