langchain-postgres
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill integrates with PostgreSQL to handle external data via
DocumentandHumanMessageobjects, which are stored and retrieved throughPGVectorStoreandPostgresChatMessageHistory(as seen inSKILL.md). - Ingestion points: The skill ingests untrusted data during document ingestion (
add_documents) and chat history recording (add_messages). - Boundary markers: The code examples do not demonstrate the use of delimiters (e.g., XML tags or triple quotes) or system instructions to ignore potential commands embedded in the retrieved text.
- Capability inventory: The skill possesses the capability to write to a database and retrieve content for prompt interpolation during similarity searches and chat history lookups.
- Sanitization: There is no evidence of input validation or output filtering for data retrieved from the database before it is provided to the agent.
Audit Metadata