Back to skill

Security audit

群消息总结

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Feishu message summarizer, with privacy considerations users should handle carefully.

Install only if you intend to summarize Feishu conversations you are allowed to access. Avoid feeding confidential, personal, or regulated chat content unless you have permission, and review summaries before sharing them or turning extracted items into documents or tasks.

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

Note
Location
Script/parse.py:116
Finding

Unpinned Third-Party Test Dependency Installation

Content
View full analysis

Vulnerability Details

File Location: Script/parse.py, line 116
Vulnerability Type: Unpinned and unverified third-party dependency installation
Risk Level: Low

Vulnerable Code:

bash
pip install pytest
pytest test_parse.py -v

Technical Analysis

The test documentation instructs users to install pytest without specifying an audited version or verifying package hashes. Consequently, the installed package is determined dynamically by the configured Python package index and dependency resolver at installation time.

Although pytest is a legitimate package, this installation procedure lacks reproducibility and supply-chain integrity controls. If the configured index is compromised, replaced, or incorrectly configured, a substituted distribution or malicious transitive dependency could be installed. Python packages may execute build backend or installation-related code during package installation.

Attack Path

  1. An attacker compromises a configured Python package repository, influences the package-resolution path, or causes the user to use an untrusted package index.
  2. The attacker serves a malicious or modified distribution matching the requested unpinned package or one of its dependencies.
  3. A user follows the documented setup command:
    bash
    pip install pytest
    
  4. pip resolves and downloads the attacker-controlled distribution because no version, source, or cryptographic hash is enforced.
  5. Malicious build or installation code executes with the privileges of the user running pip.
  6. The installed package may execute additional malicious behavior when the documented test command is subsequently run.

Impact Assessment

Successful exploitation could execute arbitrary code with the privileges of the account performing the installation. The affected scope may include the active virtual environment, project files writable by that user, accessible credentials a ...[truncated 335 chars]

Remediation
View remediation

Remediation Suggestions

  1. Move development dependencies into a dedicated lock or requirements file rather than installing them through an unpinned documentation command.
  2. Pin pytest and all transitive dependencies to reviewed versions.
  3. Generate and enforce cryptographic hashes, for example:
    bash
    python -m pip install --require-hashes -r requirements-dev.txt
    
  4. Generate the locked dependency set using a reproducible dependency-management tool and review changes before updating it.
  5. Explicitly use a trusted package index and prevent unexpected fallback to additional indexes.
  6. Install test dependencies in an isolated virtual environment with no unnecessary credentials or elevated privileges.
  7. Add automated dependency vulnerability and integrity checks to the project's maintenance workflow.
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language description, headings, examples, and usage guidance are entirely in Chinese, with no indication that other languages are supported or that Chinese is a required locale for a region-specific purpose. Under the stated policy, forcing a specific language without user opt-in is a language/locale policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is designed to analyze private or group chat content, extract participant activity, and summarize decisions and tasks, but it does not warn about privacy, sensitivity of message contents, or the need for appropriate authorization and consent. This increases the risk of users processing confidential conversations or personal data without adequate awareness, which can lead to privacy violations, oversharing, or policy noncompliance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations in natural-language content. This script's module docstrings, comments, and embedded test documentation are Chinese-only, with no opt-in or explanation that the skill is intentionally limited to Chinese-speaking users or a China-specific environment.

Content

No source excerpt is available for this finding.