Back to skill

Security audit

pikpak-dedup

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: its reported duplicate-review behavior appears purpose-aligned, though its description does not fully match its capabilities and some scan coverage is incomplete.

The verdict is benign, not a guarantee of zero risk. Before installing, consider whether filename-based candidate grouping and printed deletion commands fit your needs, and note that duration is not analyzed. The scan is marked partial because several referenced paths were not found in the bundled artifact, so the evidence is incomplete.

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 (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The code serves the same general duplicate-review purpose, but its matching method materially differs from the description: size and resolution support filtering, ranking, and evidence, while normalized names determine candidate groups, and duration is unused. It explicitly labels results as unverified name-based candidates. The no-file-movement promise is respected: the only live CLI operation is listing, and deletion commands are printed only, subject to report-digest and ID checks.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied invocation explicitly requests trash-command output rather than only duplicate reporting. Hash verification and candidate approval are safeguards, but do not make command generation part of the declared report-only purpose. The chunk does not show execution of any trash command or actual file movement, and the Python implementation is not supplied.

Content

No source excerpt is available for this finding.

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.

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/analyze_dupes.py (reported line 351)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 344, 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/analyze_dupes.py (reported line 351)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:

The advertised size/duration/resolution analysis is implemented as normalized-name grouping, with no duration analysis.

Low
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest promises duplicate and multi-version detection by size, duration and resolution, but L609–L615 group files solely by media family and normalized filename. Size and resolution support filtering, ranking or supplementary evidence elsewhere, while duration is neither collected nor compared; consequently, the report does not provide the advertised duration-based assessment.

Content

No source excerpt is available for this finding.