Back to skill

Security audit

虾皮股市罗盘

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for Chinese A-share market analysis, but it directs users to run an unpinned remote CLI package that can execute changing third-party code locally.

Review this skill carefully before installing. Its finance-analysis instructions are transparent, but only run the data command if you trust the `daxiapi-cli` package and preferably use a pinned, reviewed version in a constrained environment with only the required API token available.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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 (1)

T08 · Insecure Dependencies

Error
Location
SKILL.md:23
Finding

Execution of an Unpinned Third-Party Package

Content
View full analysis
Remediation
View remediation
market compass ``` 2. Verify the selected release before documenting it: - Confirm the expected package publisher and registry. - Review the package entry point and lifecycle scripts. - Audit direct and transitive dependencies. - Record the approved package version in the repository. 3. Enforce package integrity: - Use a lockfile that records exact transitive versions and integrity hashes. - Install with a reproducible, frozen-lockfile workflow. - Prefer an internally mirrored or allowlisted registry containing reviewed artifacts. 4. Avoid runtime package retrieval where feasible: - Vendor or package a reviewed client with the Skill. - Alternatively, require administrators to install an approved version in advance and verify its version before execution. 5. Reduce execution exposure: - Run the client in a sandbox with minimal filesystem and network access. - Provide only the API credential needed for this operation. - Do not expose unrelated environment variables, credentials, or user files. - Restrict outbound network access to the required API and approved package infrastructure. 6. Add operational verification: - Check the installed package version against an explicit allowlist before invocation. - Fail closed if the version or integrity value differs from the reviewed artifact. - Periodically review dependency advisories and deliberately update the pinned version after security assessment. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger set includes fairly broad natural-language phrases such as '市场结构分析' and '市场综合分析', which are likely to appear in ordinary finance conversations. Over-broad triggers can cause unintended skill activation, increasing the chance that the agent follows this skill in contexts where the user did not explicitly request it, leading to inappropriate financial guidance or unexpected external command suggestions.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The skill instructs users to run npx daxiapi-cli@latest, which fetches and executes the newest package version at runtime rather than a reviewed, pinned release. This creates a supply-chain execution path where a compromised upstream package, malicious update, or dependency hijack could lead to arbitrary code execution on the user's machine.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction '一律使用中文名' mandates Chinese terminology for all report content, which is a language/locale constraint expressed in natural language. The file does not offer the user a language choice or explain a justified region-specific requirement, so it violates the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The title and all instructional content are written exclusively in Chinese, and the document does not indicate that language choice is optional or that the locale restriction is required for a region-specific purpose. Under the policy, 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
95% confidence
Finding

The entire markdown file is written in Chinese and does not indicate that the skill supports other languages or that Chinese is a justified locale-specific requirement. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.