qdrant-clients-sdk

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches curated code snippets and documentation from official Qdrant domains (https://snippets.qdrant.tech).
  • [COMMAND_EXECUTION]: Uses the curl command to query the Qdrant snippets API for implementation examples.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external data from an API.
  • Ingestion points: External code snippets are retrieved via curl from https://snippets.qdrant.tech/search (SKILL.md).
  • Boundary markers: None identified in the provided instructions for managing the fetched content.
  • Capability inventory: The skill has access to the Bash tool, which could potentially be used to execute commands found in external snippets.
  • Sanitization: No validation or sanitization of the fetched external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:00 PM