ClawHub
Back to skill

Security audit

Liblib Ai Gen

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward LiblibAI client that sends user prompts to a documented third-party generation API when invoked.

Install only if you intend to use LiblibAI. Treat generated prompts, reference image URLs, and task status requests as data sent to LiblibAI, and provide only the two documented API credentials in the environment.

A.I.G

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

SkillSpector

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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill explicitly relies on environment variables for API credentials and instructs running a network-capable script, but it does not declare any tool scope or permission boundary. In an agent environment, undeclared env and network access increases the chance of over-privileged execution, secret exposure, or unintended outbound requests because reviewers and policy systems cannot accurately constrain what the skill needs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The invocation description is broad enough to match generic requests to generate images or videos, not just cases where the user specifically wants LiblibAI/Seedream/Kling. That can cause the agent to invoke this skill unexpectedly, leading to unintended use of external APIs, unnecessary credentialed network actions, and possible transfer of user prompts or data to a third-party service without sufficiently specific user intent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/liblib_client.py (reported line 37)May include surrounding context.

python
"""Make authenticated POST request to LiblibAI API."""
    params = make_sign(uri, ak, sk)
    url = f"{BASE_URL}{uri}"
    resp = requests.post(url, params=params, json=body, headers={"Content-Type": "application/json"}, timeout=30)
    resp.raise_for_status()
    data = resp.json()
    if data.get("code") and data["code"] != 0:

Static analysis

No suspicious patterns detected.