ClawHub
Back to skill

Security audit

parking-spot-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill locally records parking details so the user can find their car later; the privacy risk is real but disclosed and aligned with the skill’s purpose.

Install only if you are comfortable keeping parking history, plate numbers, notes, and photo references in a local plaintext JSON file. Avoid placing the skill directory under cloud sync on shared machines, and manually prune old entries when you no longer need them.

A.I.G

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

SkillSpector

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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
83% confidence
Finding

The skill instructs the user to run a local Python script that records parking data, which implies file-write capability, but the manifest does not declare any tool scope or permissions. Undeclared write capabilities weaken transparency and reviewability because an agent or runtime may persist data without an explicit least-privilege declaration, making misuse or unexpected data retention harder to detect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script stores sensitive location history and vehicle details such as parking locations, timestamps, license plate, notes, and payment timing in a plain JSON file on disk. On shared machines, backups, or compromised user accounts, this data can reveal movement patterns and vehicle information, creating a real privacy and personal-safety risk.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/parking_memory.py (reported line 75)May include surrounding context.

python
print("  location : %s" % (args.location or "(none)"))
    bits = []
    for k in ("level", "row", "section"):
        v = getattr(args, k)
        if v:
            bits.append("%s=%s" % (k, v))
    if bits:

Static analysis

No suspicious patterns detected.