vector-init-applications

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate workspace management tasks, such as reading and writing configuration files and processing data from local CRM files. It uses restricted shell commands (date and test) and interacts with a Pinecone index through dedicated MCP tools. No signs of credential harvesting, unauthorized data exfiltration, or obfuscation were found.
  • [PROMPT_INJECTION]: The skill processes data from external files, which presents an indirect prompt injection surface as part of its primary data-handling workflow.
  • Ingestion points: Data is ingested from crm/outreach.md and crm/opportunities.md to populate the vector store.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: The skill possesses the ability to write to the local file system and upsert records to an external Pinecone index.
  • Sanitization: The skill does not perform validation or sanitization of the text retrieved from the CRM files before concatenating it for embedding.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:16 AM
Security Audit — agent-trust-hub — vector-init-applications