Security audit

Skills of A-share futures data released by ft.tech.

Security checks for vulnerabilities and agentic risk

Overview

This futures-data skill is mostly coherent, but its network helper can follow redirects outside the disclosed market.ft.tech destination, creating a review-worthy network-scope concern.

Install only if you are comfortable allowing this skill to run local Python code that contacts market.ft.tech for futures market data. Review is warranted because redirects and unbounded reads could broaden network impact; safer packaging would disable or revalidate redirects and add timeouts and response-size limits.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: sub-skills/futures-base-data/scripts/handler.py:16
Finding: Redirect Handling Bypasses the Outbound Destination Allowlist
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: sub-skills/futures-base-data/scripts/handler.py:25
Finding: Unbounded Network Reads Permit Resource Exhaustion
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.
md
`run.py` 与本文件（`SKILL.md`）位于同一目录。执行时：

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill instructs the agent to derive and execute a local run.py via python <RUN_PY> ..., and the documented behavior includes filesystem path handling, shell execution, and outbound network access to market.ft.tech. However, the skill metadata declares no explicit tool scope or permissions boundary. This creates a real least-privilege and transparency issue: an agent may grant or assume broader capabilities than intended, making misuse or unexpected command execution harder to control and audit.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The manifest description is entirely framed around Chinese-language user requests and Chinese-name lookups, such as users asking for '期货列表' and mapping from '中文名/品种'. This indicates a language-specific interaction pattern, but the file does not offer any user language choice or document a justified locale restriction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The module docstring and CLI usage examples/messages are written only in Chinese, which imposes a specific language on users without any opt-in or language selection. The policy explicitly calls for flagging language or locale constraints when they are forced and not clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The printed usage and error strings are exclusively Chinese, so users receive operational guidance in a single forced language. Because no language choice or documented regional justification is present in this file, this is a natural-language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill’s natural-language description and title are entirely in Chinese and describe when the skill should be used, but they do not indicate that language is optional or region-specific. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The manifest description is written as an instruction keyed specifically to Chinese user utterances such as '用户问期货K线、期货日线/分钟线、周线/月线、期货历史行情时使用' and '若用户只给中文名/品种'. This implies a fixed Chinese-language invocation policy without stating that other languages are also supported or that the language constraint is intentional and user-selectable.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.