Back to skill

Security audit

pikpak-magnet-pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill downloads an approved resource through your PikPak account and only previews cloud deletion commands for separate approval.

Use a trusted CLI and your authorized account, confirm the resource and destination, and keep receipts private. Failed downloads may leave partial files. Verify downloaded content before separately approving any deletion; the local hash does not establish source authenticity.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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/magnet_pipeline.py (reported line 215)May include surrounding context.

python
if fmt_json:
        cmd += ["-F", "json"]
    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
        return proc.returncode, proc.stdout, proc.stderr
    except FileNotFoundError:
        die("找不到 PikPak CLI。安装页:https://mypikpak.com/cli")

Tainted flow: 'cmd' from os.environ.get (line 211, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/magnet_pipeline.py (reported line 215)May include surrounding context.

python
if fmt_json:
        cmd += ["-F", "json"]
    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
        return proc.returncode, proc.stdout, proc.stderr
    except FileNotFoundError:
        die("找不到 PikPak CLI。安装页:https://mypikpak.com/cli")

Download failure modifies the destination despite documentation promising otherwise (L558 and L475).

Low
Category
Excessive Agency
Confidence
98% confidence
Finding

The CLI help at L558 claims that a failed download does not change the destination directory, and the failure message at L475 repeats that guarantee. However, L462–L473 create the destination directory and download directly into a .part file within it; on failure, that partial file is deliberately retained, contradicting the documented filesystem-side-effect guarantee.

Content

No source excerpt is available for this finding.