api-vector-db-pinecone
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and retrieval of data from an external vector database, creating a potential surface for indirect prompt injection if malicious instructions are present in the stored content.
- Ingestion points: Data is ingested via
upsertinexamples/core.mdandupsertRecordsinexamples/inference.md. - Boundary markers: Code examples do not demonstrate the use of delimiters or "ignore" instructions for processed data.
- Capability inventory: The skill manages network requests to the Pinecone API and performs database operations including creation, deletion, and querying.
- Sanitization: No content sanitization or validation logic is provided for the data being indexed.
Audit Metadata