Back to skill

Security audit

Qoris Memory — Persistent Agent Memory

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent persistent-memory skill that clearly discloses its external Qoris MCP service, required user credentials, explicit save/recall tools, and cross-session storage behavior.

Install only if you want an external Qoris workspace to store agent memories. Treat QORIS_API_KEY as a secret, use a separate workspace for shared or sensitive projects, avoid saving credentials or regulated data unless your policy allows it, and review Qoris retention/deletion controls before relying on it for confidential work.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · config.example.env (reported line 2)May include surrounding context.

text
# Qoris Memory Configuration
# Copy this file to .env and fill in your credentials
# Get your credentials at qoris.ai/dashboard

# Required: Your Qoris API key

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README explicitly promotes persistent memory across sessions, team members, and projects, plus semantic search, but does not warn users not to store secrets, regulated data, or private personal/team information. In a memory skill, this omission materially increases the chance that operators will persist sensitive data and make it retrievable more broadly than intended.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README markets the agent as remembering 'everything' across sessions and team members, which encourages broad retention and sharing of user-provided information without any minimization or consent guidance. In the context of an agent memory product, this can normalize over-collection and cross-user exposure of confidential data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest advertises persistent memory operations and full document content retrieval, but it provides no user-facing disclosure about long-term data retention, retrieval scope, or the sensitivity of stored and fetched content. In an agent context, this can lead users or downstream integrators to unknowingly store sensitive information or expose complete knowledge documents across sessions, increasing privacy and data leakage risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The installation section tells users to export an API key and workspace ID but does not remind them that the API key is a secret that must not be committed, logged, or shared. This is a documentation security weakness that can lead to accidental credential exposure during setup or troubleshooting.

Content

No source excerpt is available for this finding.