Back to skill

Security audit

Ai Intelligent Employee Survey

Security checks for vulnerabilities and agentic risk

Overview

The skill describes a plausible employee survey app, but its install instructions run mutable remote code that was not included in the reviewed artifact.

Review the external repository yourself before installing, prefer a pinned audited commit or signed release, use an isolated virtual environment or container, and do not process real employee survey data until privacy, storage, retention, and access controls are verified.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:43
Finding

Mutable Remote Repository Is Retrieved and Executed Without Integrity Verification

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 43–46
Vulnerability Type: Remote payload retrieval and execution
Risk Level: High

Vulnerable Code

bash
git clone https://github.com/openclaw-skills/ai-intelligent-employee-survey
cd ai-intelligent-employee-survey
pip install -r requirements.txt
python app.py

Technical Analysis

The installation instructions clone a mutable external Git repository without selecting or verifying an immutable commit, signed tag, release artifact, or cryptographic checksum. They then install dependencies declared by the remotely retrieved repository and directly execute its app.py.

Consequently, the code executed by users is not contained in the audited project and can change after this skill has been reviewed. If the repository, its maintainer account, or its dependency configuration is compromised, the installation procedure can execute attacker-controlled Python package installation logic or application code.

The artifact contains no local implementation or dependency manifest with which to validate the advertised employee-survey privacy and anonymity properties.

Attack Path

  1. An attacker compromises the external repository, a maintainer account, or a dependency referenced by its remotely supplied requirements.txt.
  2. The attacker modifies app.py, the dependency manifest, or package installation logic to include a malicious payload.
  3. A user follows the documented installation procedure and clones the current repository state.
  4. pip install -r requirements.txt runs package installation behavior, or python app.py directly executes the altered application.
  5. The payload executes with the privileges and environmental access of the user running the commands.
  6. Depending on that user's access, the payload could read or modify local files, access credentials available to the process, communicate over the network, or access employee sur ...[truncated 503 chars]
Remediation
View remediation

Remediation Suggestions

  • Include the reviewed application source and dependency manifest in the skill package instead of relying entirely on a mutable external repository.
  • If remote retrieval is necessary, check out a specific audited commit hash rather than the repository's default branch.
  • Verify a signed release or cryptographic checksum before installing or executing retrieved content.
  • Pin every Python dependency to an exact version and trusted package index.
  • Use a hash-locked dependency file and install with pip install --require-hashes.
  • Review dependencies for malicious installation hooks, dependency confusion, and known vulnerabilities.
  • Run the application as a dedicated, unprivileged account inside an isolated virtual environment or container.
  • Restrict filesystem and network access to the minimum required for survey operation.
  • Document and implement controls for survey-data storage, anonymization, encryption, retention, access authorization, and outbound transmission.
  • Avoid instructing users to execute newly retrieved code until its provenance and integrity have been verified.
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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description and main README content present the skill exclusively in Chinese, which can amount to a language-policy violation when no user opt-in or justified locale restriction is provided. The file does not state that the skill is intended only for Chinese-speaking users or a China-specific deployment context.

Content

No source excerpt is available for this finding.