ClawHub
Back to skill

Security audit

pikpak-storage-report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only PikPak storage reporting helper, with expected local report-writing and CLI use but no evidence of deletion, persistence, or hidden account changes.

Use this only when you want an agent to enumerate a selected PikPak folder and create a local report that may reveal private file and folder names. Keep the report in a private directory, use a trusted PikPak CLI and environment, and do not treat the output as official account quota or deletion guidance.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes Python scripts, writes JSON reports, and relies on environment variables, but it does not declare a corresponding tool/permission scope. That mismatch can cause the agent runtime to grant broader implicit capabilities than reviewers expect, or to execute the skill without an explicit least-privilege contract. In a skill that touches local files and shells out to Python, undeclared capabilities materially weaken reviewability and containment even if the documented intent is read-only.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill document is written in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

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
78% confidence
Finding

The executable path comes from the PIKPAK_BIN environment variable and is passed directly to subprocess.run. If an attacker can influence the environment of the agent/skill, they can cause execution of an arbitrary program under the agent's privileges, which is especially relevant in an automated skill context even though the tool is described as read-only.

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:

Static analysis

No suspicious patterns detected.