miro-multi-env-setup

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with potentially untrusted data sources, creating a surface for indirect prompt injection attacks where malicious instructions hidden in files or documentation could influence the agent's logic.
  • Ingestion points: Uses Read, Glob, and Grep to inspect repository files (SKILL.md) and WebFetch to retrieve Miro documentation from official sources.
  • Boundary markers: The skill explicitly instructs the agent to pause for owner approval before sensitive production mutations and to fail on inconsistent environment mappings.
  • Capability inventory: The agent has the ability to modify the local file system using Write and Edit tools based on the data it processes.
  • Sanitization: The instructions do not define specific sanitization or filtering mechanisms for the data retrieved from the repository or the web.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:34 PM
Security Audit — agent-trust-hub — miro-multi-env-setup