etl-sync-job-builder
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The 'Full ETL Job Example' in 'SKILL.md' includes a code snippet that constructs a SQL 'VALUES' clause using manual string concatenation and interpolation. This pattern is susceptible to SQL injection attacks if the source data (e.g., user email) is not properly sanitized before being included in the query.\n- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by designing jobs that ingest untrusted data from external sources like APIs, files, or databases.\n
- Ingestion points: The 'extract' methods defined in 'SKILL.md' facilitate the retrieval of external data.\n
- Boundary markers: The provided templates do not include instructions or delimiters to prevent the agent from following commands embedded in the processed data.\n
- Capability inventory: The skill utilizes database write operations (Prisma upsert and raw SQL) and automated scheduling via node-cron.\n
- Sanitization: The example transformation logic does not include explicit validation, escaping, or sanitization of the ingested content.
Audit Metadata