studio-libraries

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a central library index and specific documentation files from hub.joyco.studio using curl. These operations target the vendor's own infrastructure to provide up-to-date implementation guidelines.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data (markdown and HTML content) from the library index and documentation to shape the agent's architecture and coding decisions.
  • Ingestion points: Data enters the agent's context via curl responses from hub.joyco.studio (SKILL.md, steps 1 and 3).
  • Boundary markers: The instructions do not specify delimiters or explicit instructions to ignore embedded commands within the fetched documentation.
  • Capability inventory: The agent has the capability to perform network requests (curl), write files, and execute package management commands (npm, pip, etc.) based on the ingested content.
  • Sanitization: There is no mention of sanitizing or filtering the fetched external content before it is used to influence the agent's planning phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 12:46 AM
Security Audit — agent-trust-hub — studio-libraries