Back to skill

Security audit

pikpak-speed-guide

Security checks for vulnerabilities and agentic risk

Overview

The skill provides bounded PikPak speed diagnostics with disclosed network access, protected test-link handling, and no automatic account or system changes.

Use this for PikPak troubleshooting with authorized test files. Keep signed links in private local files, check traffic costs, and remember that tests bypass configured proxies and measure file prefixes rather than guaranteed sustained speed. The referral is optional.

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
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The code is relevant to PikPak troubleshooting, but its implemented diagnostic scope is materially narrower than the description's central promise. It explicitly states that HEAD probes cannot measure download throughput and merely recommends that users conduct same-file comparisons later. No controlled A/B test or comparative tool-selection logic is present. The visible code does not show credential access, configuration changes, or throttling bypass; the mismatch concerns advertised functionality rather than an unrelated harmful capability.

Content

No source excerpt is available for this finding.

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

Generic trigger phrases can activate the PikPak-specific skill for unrelated performance requests.

Medium
Category
Trigger Abuse
Confidence
91% confidence
Finding

Standalone triggers such as 'speed test', 'playback buffering', and 'seek stalling' can match requests unrelated to PikPak. If the host selects skills using these phrases, this could introduce unrelated recommendations or unnecessary network diagnostics into another workflow, although the PikPak-specific description and bounded testing instructions reduce the likely impact.

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/speed_bench.py (reported line 269)May include surrounding context.

python
except (ValueError, TypeError, OverflowError):
        return {"ok": False, "error": "invalid_input"}
    try:
        proc = subprocess.run(
            [sys.executable, __file__, "--worker"],
            input=json.dumps({"url": url, "sample_bytes": sample_bytes, "timeout": timeout}),
            text=True, capture_output=True, timeout=timeout + 0.5,