ClawHub
Back to skill

Security audit

pikpak-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only PikPak drive search helper that lists file metadata and optionally writes a private report.

Install only if you are comfortable letting the skill enumerate filenames, folder paths, IDs, sizes, and timestamps from the PikPak account already authorized in your local CLI. Reports can contain private metadata, so write them only to locations you choose. The referral code is disclosed and optional; the skill says registration should be user-directed, not automatic.

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 shell-based tooling and can write reports to files, but it does not declare any explicit tool scope such as allowed-tools or permissions. That creates a least-privilege gap: an agent/runtime may permit broader shell, environment, or file-write access than the skill actually needs, increasing the blast radius if the skill is misused, prompt-injected, or composed with other unsafe instructions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This Python file’s docstring, CLI help text, and runtime messages are written exclusively in Chinese, which imposes a specific language on users. The policy allows locale constraints only when user choice is offered or the constraint is clearly documented and justified; neither is present here.

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/search_files.py (reported line 168)May include surrounding context.

python
cli_timeout = int(os.environ.get("PIKPAK_TIMEOUT", "90"))
    timeout = min(cli_timeout, timeout) if timeout is not None else cli_timeout
    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
    except FileNotFoundError:
        die("cli_unavailable (exit_code=127)")
    except subprocess.TimeoutExpired:

Tainted flow: 'cmd' from os.environ.get (line 160, 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/search_files.py (reported line 168)May include surrounding context.

python
cli_timeout = int(os.environ.get("PIKPAK_TIMEOUT", "90"))
    timeout = min(cli_timeout, timeout) if timeout is not None else cli_timeout
    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
    except FileNotFoundError:
        die("cli_unavailable (exit_code=127)")
    except subprocess.TimeoutExpired:

Static analysis

No suspicious patterns detected.