addon-jsonl-chunking-citations

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill defines a standard data processing workflow for document chunking and metadata extraction.
  • [DATA_EXFILTRATION]: The skill interacts with internal data storage (Postgres tables such as 'document_pages' and 'document_chunks', and object storage paths). These operations are the primary intended purpose of the skill and do not involve external exfiltration to unauthorized domains.
  • [PROMPT_INJECTION]: The skill processes potentially untrusted document content from 'raw_markdown'. While it does not explicitly define sanitization logic, its role is limited to structuring data for storage, which carries low risk for immediate instruction override.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 06:54 PM