roboflow-universe

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill instructions facilitate searching for public datasets and models via the official Roboflow Universe platform. All referenced URLs (universe.roboflow.com) and repositories (github.com/roboflow/computer-vision-skills) are trusted vendor domains and assets.
  • [NO_CODE]: The skill consists exclusively of markdown documentation and does not contain any executable scripts, binaries, or package installations.
  • [SAFE]: Analysis of indirect prompt injection surfaces (Category 8):
  • Ingestion points: The universe_search tool returns dataset descriptions and metadata from external contributors on Roboflow Universe.
  • Boundary markers: The skill does not provide specific instructions to the agent to treat this metadata as untrusted data.
  • Capability inventory: The skill does not include any dangerous capabilities like file system writes or code execution; it is restricted to searching and providing documentation.
  • Sanitization: No sanitization logic is present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 11:10 PM
Security Audit — agent-trust-hub — roboflow-universe