Back to skill

Security audit

Volcengine Documentation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Volcengine documentation lookup helper, with expected external API calls but no hidden persistence, credential access, or destructive behavior.

Install only if you want Volcengine documentation lookups through Volcengine's docs API. Do not include credentials, internal prompts, private system details, or non-Volcengine private URLs in search or fetch inputs, because those values may be sent to the external documentation service.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill invokes network-capable functionality through documented search/fetch endpoints and local scripts, but it does not declare any explicit tool scope such as allowed-tools or permissions. This creates a governance gap where the runtime or reviewer cannot easily constrain or audit outbound access, increasing the risk of unintended network use or future expansion beyond the intended documentation API.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says that any request involving Volcengine product consultation, usage questions, or documentation lookup should preferentially invoke this skill, which is an overly broad trigger. Broad routing increases the chance the skill is activated for ordinary conversations unnecessarily, causing over-collection of user queries, excessive external lookups, or inappropriate tool use when a simple model response would suffice.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The search function transmits arbitrary user-supplied queries to an external documentation API. In an agent context, users may unknowingly send secrets, internal prompts, or sensitive operational data to a third-party service, creating a data exfiltration/privacy risk even though the destination is the intended vendor endpoint.

Content

Scanner excerpt · scripts/volcengine_docs.py (reported line 26)May include surrounding context.

python
"Content-Type": "application/json"
    }
    try:
        response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT)
        response.raise_for_status()
        return response.json()
    except Exception as e:

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The fetch function sends a user-provided URL to an external API without validating that it belongs to the expected Volcengine documentation domain. Although the local script does not fetch the URL directly, this still enables external transmission of arbitrary URLs and may cause the upstream service to retrieve unintended resources, increasing privacy risk and potential abuse of the remote fetch capability.

Content

Scanner excerpt · scripts/volcengine_docs.py (reported line 46)May include surrounding context.

python
"Content-Type": "application/json"
    }
    try:
        response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT)
        response.raise_for_status()
        result = response.json()
        # 始终返回纯净URL

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The user-facing help text and examples are entirely in Chinese, and the script's messages and descriptions assume a Chinese locale without any opt-in or alternative language path. Under the stated policy, forcing a specific language without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.