T09 · Insecure Skill Coding Practices
- Location
scripts/model-catalog-updater.py:46- Finding
API Credential Disclosure and SSRF Through Unvalidated Provider Endpoint
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/model-catalog-updater.py:46API Credential Disclosure and SSRF Through Unvalidated Provider Endpoint
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.
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.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
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
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
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