bulk-json-import-progress

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external JSON data into a local database, establishing an attack surface where malicious content in the input file could potentially influence the agent's context.
  • Ingestion points: The import function described in SKILL.md accepts a json string parameter from an external source.
  • Boundary markers: There are no specific boundary markers or instructions to the agent to disregard instructions within the processed JSON content.
  • Capability inventory: The skill performs database write operations using localDataSource.insertSongs.
  • Sanitization: The implementation includes data normalization via MusicVideoType.normalize and performs validation on referenced IDs before insertion.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 07:02 AM
Security Audit — agent-trust-hub — bulk-json-import-progress