miro
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the
@useclawlink/clipackage from the npm registry usingnpxat runtime to facilitate Miro interactions. - [COMMAND_EXECUTION]: Relies on shell commands to perform Miro actions. The skill documentation notes that credentials for this interaction are stored locally in the
~/.clawlink/credentials.jsonfile. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection when handling untrusted data.
- Ingestion points: External data enters the context through actions like
miro_create_document_item(URL-based) andmiro_create_image_item_using_local_file(local file access) defined inSKILL.md. - Boundary markers: The skill instructions in
SKILL.mddo not include boundary markers or specific prompts to ignore embedded instructions within processed data. - Capability inventory: The agent can execute shell commands via
npxand perform authenticated write operations on Miro boards. - Sanitization: There is no evidence of content sanitization or validation for the external resources processed by the Miro actions.
Audit Metadata