miro-rate-limits

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The skill ingests untrusted data from the local repository using Read, Glob, and Grep, and fetches external content from Miro's developer documentation using WebFetch (e.g., in SKILL.md and references/official-docs.md).
  • Boundary markers: There are no explicit delimiters or specific warnings to ignore instructions embedded within the data being processed.
  • Capability inventory: The agent has the capability to modify the repository filesystem using the Write and Edit tools based on the data it processes.
  • Sanitization: While instructions mention using "sanitized" headers, there is no technical enforcement or validation mechanism described for the broader ingestion of repository files or web content.
  • [SAFE]: The skill adheres to security best practices by explicitly instructing the agent never to print or expose sensitive credentials such as access tokens, refresh tokens, client secrets, or authorization codes. Furthermore, network access via WebFetch is constrained to official, well-known Miro domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:34 PM
Security Audit — agent-trust-hub — miro-rate-limits