qdrant

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it retrieves and processes content from an external vector database.
  • Ingestion points: Data returned from search and collection queries via curl in SKILL.md.
  • Boundary markers: Absent; database payloads are returned to the agent without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill utilizes curl for network operations and jq for JSON processing, allowing it to read and write data to the configured Qdrant instance.
  • Sanitization: Absent; the results from the database are processed raw without filtering or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:15 AM