Back to skill

Security audit

Api Model list updater

Security checks for vulnerabilities and agentic risk

Overview

This skill has a legitimate model-catalog purpose, but it can send local or environment-backed API credentials to arbitrary configured provider URLs without destination validation.

Review each provider baseUrl before using this skill, especially entries using env: API keys. Avoid running it against untrusted, plaintext HTTP, private-network, or recently changed provider URLs unless you are sure no sensitive credential will be sent there. Expect it to modify OpenClaw model defaults after you select models, although it creates a backup first.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/model-catalog-updater.py:46
Finding

API Credential Disclosure and SSRF Through Unvalidated Provider Endpoint

Content
View full analysis
Remediation
View remediation
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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill describes capabilities that read configuration, write backups and updated config files, and query provider endpoints, but it declares no explicit tool scope or permissions. That mismatch increases the chance the runtime grants broader-than-necessary access, making unintended file modification or network use harder to constrain and review.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language triggers are broad phrases like 'show me available models' and 'what models are on lmstudio', which can overlap with ordinary conversation and accidentally invoke the skill. Because the skill performs network queries and edits configuration files, accidental activation could lead to unintended external requests and persistent config changes.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 140)May include surrounding context.

md
Your configured providers:
1. qwen-portal (https://portal.qwen.ai/v1)
2. lmstudio (http://192.168.56.1:1234/v1)
3. xai (https://api.x.ai/v1)
4. openrouter (https://openrouter.ai/api/v1)
5. modal-direct (https://api.us-west-2.modal.direct/v1)
6. cloudflare-ai-gateway

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 142)May include surrounding context.

md
2. lmstudio (http://192.168.56.1:1234/v1)
3. xai (https://api.x.ai/v1)
4. openrouter (https://openrouter.ai/api/v1)
5. modal-direct (https://api.us-west-2.modal.direct/v1)
6. cloudflare-ai-gateway
7. minimax