t2000-services

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill metadata references a requirement for the @t2000/cli package from a public registry.- [COMMAND_EXECUTION]: The instructions guide the agent to perform operations using the t2 command-line utility for marketplace discovery and job management.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a remote marketplace API which may contain untrusted content.
  • Ingestion points: Marketplace listings are retrieved from https://api.t2000.ai/v1/services via the t2 services command in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between tool instructions and data content from the marketplace.
  • Capability inventory: The skill possesses the ability to execute system commands via the t2 CLI.
  • Sanitization: No sanitization or validation logic is specified for the data retrieved from the remote marketplace.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:38 PM
Security Audit — agent-trust-hub — t2000-services