memory-qdrant

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches a pre-trained machine learning model (~25MB) from Hugging Face's official repository (huggingface.co) during the initial execution. This is a well-known service and the download is essential for local embedding generation as described in the documentation.\n- [PROMPT_INJECTION]: Contains a potential indirect prompt injection surface as it ingests untrusted user data for later recall. However, it implements a robust evidence chain of mitigations:\n
  • Ingestion points: Messages are captured in the agent_end hook in index.js.\n
  • Boundary markers: Recalled memories are wrapped in <relevant-memories> tags with explicit instructions for the AI to ignore embedded commands.\n
  • Capability inventory: Limited to memory management tools (store, search, forget) with no arbitrary command execution.\n
  • Sanitization: The sanitizeInput function in index.js removes HTML tags and control characters from all stored text.\n- [SAFE]: Implements a default privacy protection layer that uses regular expressions to detect and skip the automatic capture of PII, such as emails and phone numbers, unless the user explicitly enables the allowPIICapture configuration.\n- [SAFE]: Data persistence is handled locally using the filesystem. Memories are saved to a user-controlled directory (~/.openclaw-memory/) in a standard JSON format, ensuring transparency and preventing unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 03:50 AM