ClawHub
Back to skill

Security audit

yance-report-gen

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language investment report generator that reads specified JSON inputs and writes a Markdown report, with no evidence of hidden network access, persistence, exfiltration, or destructive behavior.

Installers should understand that the skill is intended for Chinese-language teaching/demo investment reports. Provide only the JSON report files you want it to read, and choose a deliberate output directory because the script will create that directory and write a dated Markdown report there.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill documentation exposes file read/write operational behavior via the referenced report-generation script, but it does not declare any explicit tool scope, permissions, or path restrictions. That creates an authorization ambiguity: a runner may grant broader filesystem access than the skill actually needs, increasing the chance of unintended reads or overwrites if inputs or output paths are abused.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring states the report generator identity and behavior entirely in Chinese, and the implementation consistently emits Chinese-only report content. For SQP-3, this is a natural-language locale policy issue because the skill does not offer any language choice or document a justified region-specific limitation.

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/generate_report.py (reported line 218)May include surrounding context.

python
parser.add_argument("--stocks", default="", help="标的列表（逗号分隔）")
    args = parser.parse_args()

    report_files = {role: getattr(args, f"{role}_report") for role in ROLES}
    result = generate_report(report_files, args.stocks, args.output)
    if args.output != ".":
        print(json.dumps(result, ensure_ascii=False))