querying-from-seekdb
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions prompt the installation of the official
pyseekdblibrary, along withpandasandopenpyxlfor data processing and export functions. - [COMMAND_EXECUTION]: The skill operates by executing a local Python script (
scripts/query_from_seekdb.py) using arguments derived from user queries. This is the intended primary function of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from the SeekDB database. If documents or metadata within the database contain malicious instructions, they could potentially influence the agent's subsequent behavior when it processes the query results.
- Ingestion points: Data enters the context via the
collection.get()andhybrid_search()methods inscripts/query_from_seekdb.py. - Boundary markers: None identified in the script's output to the agent.
- Capability inventory: The script has capabilities to read from the network (SeekDB server) and write to the local filesystem (CSV/Excel export).
- Sanitization: No specific content sanitization or filtering is applied to the retrieved database records before they are displayed or exported.
Audit Metadata