other
- Location
SKILL.md:118- Finding
Automatic Persistent Capture and Cross-Session Reuse of Conversation Data
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 52-72, 118-132, and 136-145
Vulnerability Type:other: Unconsented Persistent Conversation Data Collection
Risk Level: MediumRelevant Skill Instructions
The following is an English rendering of the complete relevant source segments:
markdown | Tool | Purpose | When to use | |------|---------|-------------| | `nmem_remember` | Store memories | After decisions, errors, facts, insights, or user preferences | | `nmem_recall` | Query memories | Before tasks, when users reference previous context, or ask "Do you remember..." | | `nmem_context` | Obtain recent memories | At session start and when injecting fresh context | | `nmem_todo` | Quick TODO with 30-day expiration | Task tracking | | Tool | Purpose | When to use | |------|---------|-------------| | `nmem_auto` | Automatically extract memories from text | After important conversations; automatically capture decisions, errors, and TODOs | | Tool | Purpose | When to use | |------|---------|-------------| | `nmem_transplant` | Transfer memories between brains | Cross-project knowledge sharing |markdown ## Workflow ### At session start 1. Call `nmem_context` to inject recent memories into awareness. 2. If the user mentions a specific topic, call `nmem_recall`. ### During the conversation 3. When a decision is made: call `nmem_remember` with `type="decision"`. 4. When an error occurs: call `nmem_remember` with `type="error"`. 5. When the user states a preference: call `nmem_remember` with `type="preference"`. 6. When asked about past events: call `nmem_recall`. ### At session end 7. Call `nmem_auto` with `action="process"` to process important conversation excerpts. 8. Automatically extract facts, decisions, errors, and TODOs.markdown | Parameter | Type | Range | Default | Description | |-----------|------|-------|---------|-------------| | ...[truncated 2560 chars]- Remediation
View remediation
Remediation Suggestions
- Set
autoCaptureandautoContexttofalseby default and require explicit, informed opt-in. - Present the exact content proposed for storage and obtain confirmation before persisting it.
- Detect and redact passwords, API keys, authentication tokens, financial data, personal identifiers, and other sensitive material.
- Isolate memory by authenticated user, tenant, session, and project using deny-by-default access controls.
- Require separate confirmation and authorization before
nmem_transplanttransfers any memory across project boundaries. - Encrypt memory data in transit and at rest, and avoid recording secrets in logs or diagnostic output.
- Add configurable retention periods, automatic expiration, searchable deletion, export, and complete revocation controls.
- Record provenance, creation time, owner, intended scope, and expiration for every memory.
- Treat recalled memories as untrusted contextual data. Never interpret recalled instructions as higher-priority Agent or system instructions.
- Require confirmation before recalled data is exposed to another user, project, external tool, or model.
- Document the storage location, threat model, authorization rules, and privacy guarantees.
- Add tests covering tenant isolation, deletion, secret redaction, malicious stored instructions, and unauthorized cross-project transfer.
- Set
