Back to skill

Security audit

PC Build Assistant

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: its completed scan found no AIG issues, and the noted findings are limited risks judged consistent with its purpose.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable with the undeclared file-reading and network capabilities, the possible unbounded query output, and the laptop-scope mismatch. The scan reports complete coverage of 36 components, with the listed findings assessed as expected for the purpose.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (5)

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

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.

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · scripts/query_components.py (reported line 1822)May include surrounding context.

python
def query(category=None, budget=None, platform=None, color=None,
          rgb=None, limit=DEFAULT_QUERY_LIMIT, has_price_only=True, showcase=None,
          include_legacy=False, sort="asc", socket=None, chipset=None,
          memory_gen=None, form_factor=None, max_length=None, max_cooler_height=None,
          gpu_cooling="air",
          gpu_chip=None, min_vram=None, min_capacity=None, include_workstation_gpu=False,
          resolution=None, min_refresh=None, air_flow=None, dust_filter=None,

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · scripts/query_components.py (reported line 2133)May include surrounding context.

python
def query_all(budget=None, platform=None, color=None, rgb=None, limit=5,
              has_price_only=True, include_legacy=False, sort="asc", socket=None,
              chipset=None, memory_gen=None, form_factor=None, max_length=None,
              gpu_cooling="air", gpu_chip=None, min_vram=None, min_capacity=None,
              include_workstation_gpu=False, showcase=None, air_flow=None, dust_filter=None,
              model=None, item_id=None, max_capacity=None, integrated_graphics=None,

Hardware guidance explicitly includes laptops despite the manifest excluding them.

Low
Category
Excessive Agency
Confidence
90% confidence
Finding

L62 instructs the assistant to recommend manufacturer performance modes for laptops as well as compact desktop systems. This extends the skill's advisory behavior to a device category explicitly excluded by the manifest's 'Do not use for laptops' boundary.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/query_components.py (reported line 2429)May include surrounding context.

python
"budget", "max_length", "max_cooler_height", "min_vram", "min_capacity", "max_capacity",
        "fan_size", "radiator_bundle", "min_refresh", "min_pcie_slots", "limit",
    ):
        value = getattr(args, name)
        if value is not None and value <= 0:
            parser.error(f"--{name.replace('_', '-')} must be greater than 0")
    if (