Back to skill

Security audit

tianyancha-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple China company-information lookup guide that uses expected third-party business-data APIs, with supply-chain and credential-handling cautions but no hidden or automatic behavior.

Before installing or using this skill, confirm you intend to use Chinese company-data services, keep API tokens out of shared logs or prompts, review each provider's fees and legal terms, and install any optional Python SDK in an isolated environment with a pinned trusted version.

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:45
Finding
Unpinned Third-Party Python Package Installation## Vulnerability Details **File Location**: `SKILL.md`, line 45 **Vulnerability Type**: Unpinned and unverified third-party dependency **Risk Level**: Medium ```bash pip install tianyancha ``` ### Technical Analysis The documented installation command retrieves the latest available version of the `tianyancha` package from pip's configured package index. It does not specify an audited version, verify package hashes, identify an authoritative publisher, or use a dependency lockfile. Python package installation may execute package-controlled build or installation logic. Consequently, compromise of the referenced package, its publisher account, or the configured package index could cause attacker-controlled code to execute during installation. The repository does not include the package implementation or other evidence establishing that this dependency is an official, reviewed SDK. ### Attack Path 1. An attacker compromises the referenced package, its publisher account, or a package index used by the victim. 2. The attacker publishes a malicious release containing installation-time or import-time code. 3. A user follows the Skill documentation and runs `pip install tianyancha`. 4. Because no exact version or integrity hash is required, pip resolves and downloads the malicious release. 5. Attacker-controlled code executes during package installation or when the package is subsequently imported. ### Impact Assessment Successful exploitation could execute arbitrary code with the privileges of the user running pip or the Python application. Depending on those privileges, the attacker could access application files, environment variables, API credentials, local user data, and network resources; alter the Python environment; or install additional payloads. The scope is normally limited to the installing user's permissions unless installation is performed with elevated privileges.
Remediation
## Remediation Suggestions - Confirm that the package is an official or otherwise trusted SDK and document its authoritative publisher and repository. - Pin a reviewed, exact version rather than resolving the latest release. - Record cryptographic hashes in a requirements file and install with `pip install --require-hashes -r requirements.txt`. - Use a lockfile and a controlled package index or approved internal mirror. - Review package source, release history, and transitive dependencies before approval. - Perform installation inside an isolated virtual environment or container without administrative privileges. - Add automated dependency vulnerability, provenance, and integrity checks to the maintenance process.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Content
### 获取企业信息

```bash
curl "https://api.qichacha.com/ECIV4/GetEnterpriseByName?keyword=腾讯" \
  -H "Authorization: YOUR_TOKEN"
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The file’s title and description present the skill in Chinese only, and there is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy for natural-language violations, forcing a specific language without user opt-in should be flagged unless clearly justified.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The description and keywords are explicitly Chinese/China-specific, which indicates a locale-specific skill context. Because the file does not document that this locale restriction is optional, user-selectable, or justified as a region-specific tool, it may violate the language/locale policy requirement.

Static analysis

No suspicious patterns detected.