miro-common-errors

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and diagnostic commands for Miro API troubleshooting.
  • [COMMAND_EXECUTION]: The skill uses standard shell commands to interact with the Miro API. Sensitive information like tokens and secrets are correctly referenced through environment variables (e.g., $MIRO_ACCESS_TOKEN, $MIRO_CLIENT_SECRET), which follows secure development practices for secret management.
  • [EXTERNAL_DOWNLOADS]: Network operations target official Miro domains (api.miro.com, status.miro.com). These are recognized well-known service endpoints required for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from Miro API responses.
  • Ingestion points: API responses from api.miro.com captured via curl in SKILL.md examples.
  • Boundary markers: No explicit delimiters are used for the interpolated output.
  • Capability inventory: Shell command execution via curl, jq, and grep across the provided examples.
  • Sanitization: Responses are structured JSON and are filtered using jq to extract specific fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:34 PM
Security Audit — agent-trust-hub — miro-common-errors