Back to skill

Security audit

a-share-daily-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent market-report generator that fetches public market data locally, with ordinary dependency and routing cautions but no evidence of hidden, destructive, or data-stealing behavior.

Install in a virtual environment and pin dependencies if you need stronger supply-chain control. Use the skill only when you want a factual market-data report, and remember that its output is explicitly not investment advice.

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

Warning
Location
SKILL.md:19
Finding

Unpinned Third-Party Dependencies Create a Supply-Chain Risk

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 19-23
Vulnerability Type: Unpinned and integrity-unverified package installation
Risk Level: Medium

bash
pip install --quiet akshare pandas

Alternative installation instructions repeat the same unsafe dependency resolution behavior:

bash
pip install --user --quiet akshare pandas

Technical Analysis

The installation instructions retrieve the latest available versions of akshare, pandas, and their transitive dependencies without exact version constraints or cryptographic hashes. This makes installations non-reproducible and prevents pip from verifying that dependencies match artifacts previously reviewed by the project maintainers.

If a package release, transitive dependency, package-index account, or configured package source is compromised, following these instructions could install attacker-controlled code. Python packages can execute code during installation through build backends, and dependency code also executes when imported or invoked. The project provides no lock file, hash-verified requirements file, or trusted-index enforcement to reduce this exposure.

No evidence was found that the currently named packages are malicious. The vulnerability is the unsafe dependency acquisition process rather than a confirmed compromise of either package.

Attack Path

  1. An attacker compromises a dependency release, maintainer account, transitive dependency, or package source used by pip.
  2. The attacker publishes a malicious version that satisfies the unconstrained installation request.
  3. A user follows the documented pip install command.
  4. Pip resolves and downloads the attacker-controlled artifact because no approved version or hash is specified.
  5. Malicious code executes during package build or installation, or later when scripts/daily_review.py imports and uses the dependency.
  6. The payload runs with the permissions ...[truncated 731 chars]
Remediation
View remediation

Remediation Suggestions

  1. Create a dependency lock or requirements file containing reviewed, exact versions for all direct and transitive dependencies.
  2. Record approved artifact hashes and install with pip's hash enforcement:
    bash
    python3 -m pip install --require-hashes -r requirements.txt
    
  3. Generate and review the locked dependency set using a tool such as pip-tools, and update it through a controlled dependency-review process.
  4. Require an isolated virtual environment rather than recommending user-wide installation:
    bash
    python3 -m venv .venv
    . .venv/bin/activate
    python3 -m pip install --require-hashes -r requirements.txt
    
  5. Configure installation to use an explicitly trusted package index or an organization-controlled artifact mirror.
  6. Add automated dependency scanning and provenance checks to the release process.
  7. Replace mutable upgrade guidance such as unrestricted pip install -U akshare with instructions to install a newly reviewed and hash-pinned dependency set.
  8. Avoid running package installation with administrator or root privileges.
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README advertises very broad trigger phrases such as '今日复盘', 'A股日报', and especially the English phrase 'global market review', which can overlap with many ordinary user requests and cause unintended invocation. In an agent setting, ambiguous routing can expose user prompts or trigger market-analysis behavior when the user did not clearly ask for this specific skill, creating prompt-confusion and misexecution risk rather than a code-execution issue.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises broad trigger phrases such as '今天股市怎么样' and '全球市场', which can overlap with ordinary conversation about markets rather than an explicit request to invoke this skill. In an agent system, this increases the chance of unintended skill activation, causing the model to run local scripts, install packages, or fetch external market data when the user only wanted a casual discussion or a different tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The documented invocation examples prioritize Chinese phrases ("今日复盘" and "A股日报") and do not state that users may choose their preferred language or locale. For a general-purpose global market skill, this can create an avoidable language/locale constraint unless clearly presented as optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains natural-language strings for the module description, CLI help, errors, and output entirely in Chinese, which effectively constrains the skill to a single language. Under the policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.