importing-to-seekdb

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from CSV and Excel files, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Data enters the agent's context through scripts/import_to_seekdb.py and scripts/read_excel.py which use pandas to read content from local files provided by the user.
  • Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potentially malicious content embedded within the tabular data files.
  • Capability inventory: The skill possesses capabilities to read files, write CSVs, and perform collection management (create, add, delete) on a seekdb database via the pyseekdb SDK.
  • Sanitization: The clean_dataframe function performs type casting and handles missing values for compatibility with the database, but it does not inspect or sanitize the textual content of columns for instructions that could target the AI agent during subsequent retrieval operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:41 AM
Security Audit — agent-trust-hub — importing-to-seekdb