Back to skill

Security audit

Scp Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple SCP file-transfer wrapper whose network file-copy behavior is clear and purpose-aligned, though users should verify paths and destinations carefully.

Install only if you want an agent to perform SCP transfers. Before use, check the exact source path, destination host, account, and remote path, because SCP can send local data to another machine and may overwrite remote files.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill describes shell-capable behavior for copying files to and from remote hosts, but it does not declare any tool scope such as allowed-tools or permissions. This weakens enforcement and reviewability, because an agent may invoke shell functionality without explicit restriction, increasing the chance of unintended command execution or misuse during file transfer tasks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill encourages SCP-based transfers to remote hosts but does not warn users that actions may overwrite destination files or transmit sensitive local data off-host. In an agent setting, the lack of a clear warning increases the risk of accidental data exfiltration, overwriting backups, or sending files to the wrong remote system.

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 · scripts/scp.py (reported line 8)May include surrounding context.

python
parser.add_argument('src')
parser.add_argument('dst')
args = parser.parse_args()
subprocess.run(['scp', args.src, args.dst])

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script invokes the external scp command directly via subprocess.run(...), which can initiate network transfer of files. While the docstring names the tool, the file contains no confirmation prompt, logging, or explicit warning to the user about performing a network copy operation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.