Back to skill

Security audit

weread-ai-brain

Security checks for vulnerabilities and agentic risk

Overview

The skill’s access to private WeRead data is disclosed, limited to its reading-analysis purpose, and subject to explicit user confirmation.

Configure the key through your environment rather than chat. Confirm which books and private notes may enter the agent’s context, and review export contents and paths before saving. The artifacts do not substantiate the pre-scan malicious signal.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Code capability 'file_read' detected in tests/test_static_contracts.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
55% confidence
Finding

The skill uses 'file_read' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_static_contracts.py (reported line 68)May include surrounding context.

python
)

    def test_command_stops_before_reading_credentials_without_confirmation(self) -> None:
        result = subprocess.run(
            [sys.executable, str(SCRIPT), "shelf"],
            check=False,
            capture_output=True,