Back to skill

Security audit

Forecast Valuation

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly builds a local Excel valuation workbook, but it insecurely stores API secrets and presents hard-coded example financial data as professional analysis.

Review before installing. Use this only as a template/demo unless you verify or replace the financial data and formulas yourself. Do not enter real Gangtise or Tushare credentials unless the plaintext config.json storage is acceptable in your environment; prefer temporary credentials or environment-managed secrets, and avoid relying on the advertised upload/API features because they are not actually implemented in the inspected scripts.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/configure.py:29
Finding

API credentials are displayed and stored in plaintext

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
docs/README.md:60
Finding

Third-party dependencies are installed without version or integrity pinning

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill documents scripts that read configuration, fetch remote data, and write Excel outputs, but it declares no explicit tool scope or permissions boundary. In an agent environment, missing scope declarations can cause over-broad default access and prevent users from understanding that local file read/write behavior is required.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill describes automatic retrieval from Gangtise/Tushare and use of configured API credentials, but it does not warn users about outbound network access or credential use. In practice this can lead to unintended disclosure of queries, metadata, or financial targets to third-party APIs and may surprise users operating in restricted or confidential environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises an upload-to-Baidu-Netdisk option for generated valuation models without a clear warning that files may be transmitted off the local system. Because these spreadsheets can contain proprietary financial assumptions, API-derived data, and analyst work product, users may unintentionally exfiltrate sensitive information to a third-party service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description and usage instructions are written entirely in Chinese, including all operational guidance and examples. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in, and this README does not provide any alternative language option or justification for the restriction.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script advertises a professional, complete financial forecasting and valuation model, but most sheets are populated with hard-coded example values and formulas unrelated to the user inputs. In a finance context, this can mislead users into treating illustrative data as company-specific analysis, creating material decision risk despite no code-execution primitive being present.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module description is presented in Chinese and positions the tool as a Chinese-language financial model builder. In this file, user-facing labels, sheet names, CLI help text, and console output are also hard-coded in Chinese, with no indication that another language can be selected, which conflicts with the policy against forcing a specific language without opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The sensitivity analysis sheet claims to reflect model-based valuation sensitivity, but the code explicitly generates simulated placeholder numbers from a simple heuristic. Because the workbook presents these values as analytical outputs, users may rely on fabricated sensitivity ranges when assessing valuation uncertainty.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script collects API credentials interactively and persists them to config.json in plaintext, with no masking beyond terminal input behavior, no warning to the user, and no file permission hardening. If the working directory is shared, synced, committed to version control, or readable by other local users/processes, these secrets can be exposed and abused to access third-party financial data services.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The file mixes an English heading with overwhelmingly Chinese instructions and examples, effectively forcing a specific language for core usage without stating that the skill is China-region or Chinese-language only. The policy allows locale constraints when documented and justified, but no explicit opt-in or justification is provided here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

Nearly all user-visible strings and instructions are in Chinese, and the script does not provide any option to select another language. This can violate language/locale policy when a skill imposes a specific language without user opt-in or justification.

Content

No source excerpt is available for this finding.