skills/vm0-ai/vm0-skills/oddpool/Gen Agent Trust Hub

oddpool

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network requests to the Oddpool API at oddpool.com. These requests are necessary for the skill's primary function and are limited to the service's own infrastructure. No unauthorized exfiltration of local sensitive data was observed.
  • [COMMAND_EXECUTION]: The skill provides a curl usage example for API interaction. It correctly utilizes an environment variable ($ODDPOOL_API_KEY) for authentication, which is a standard security practice to prevent credential leakage. It also references a troubleshooting tool zero doctor, which is associated with the vendor's platform.
  • [PROMPT_INJECTION]: The skill processes data from external API endpoints, which creates a surface for indirect prompt injection.
  • Ingestion points: Responses from Oddpool API endpoints (oddpool.com).
  • Boundary markers: Not present in the usage instructions.
  • Capability inventory: Use of curl for network retrieval and jq for data parsing.
  • Sanitization: No explicit sanitization or validation logic for external API content is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 07:13 AM
Security Audit — agent-trust-hub — oddpool