Back to skill

Security audit

pikpak-storage-report

Security checks for vulnerabilities and agentic risk

Overview

The inspected skill coherently provides an authorized PikPak storage report without changing cloud files.

Use a trusted PikPak CLI and explicitly approve the folder before scanning. Omitting the folder selects the drive root, and --depth only limits display. Keep reports private and choose a dedicated output file because existing reports are overwritten. Live-service compatibility and the referenced development tests were not verified.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • 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_write, 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.

Several standalone triggers describe generic storage problems or large files without requiring PikPak context.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

Standalone triggers such as “大文件” and “ストレージ不足” can select this PikPak-specific skill for unrelated large-file or storage questions, creating an overly broad routing scope. The immediate consequence is inappropriate workflow selection rather than demonstrated unauthorized access; the requirement to confirm an authorized folder and obtain separate cloud-scan authorization substantially limits the risk.

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/storage_report.py (reported line 238)May include surrounding context.

python
cmd += ["-t", page_token]
    timeout = timeout_seconds()
    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
    except FileNotFoundError:
        raise ScanError("找不到只读 CLI;请独立检查安装。", code="CLI_UNAVAILABLE") from None
    except subprocess.TimeoutExpired:

Tainted flow: 'cmd' from os.environ.get (line 231, 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/storage_report.py (reported line 238)May include surrounding context.

python
cmd += ["-t", page_token]
    timeout = timeout_seconds()
    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
    except FileNotFoundError:
        raise ScanError("找不到只读 CLI;请独立检查安装。", code="CLI_UNAVAILABLE") from None
    except subprocess.TimeoutExpired: