background-removal

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation instructions and additional functionality from the inference-sh GitHub repository and official platform URLs.
  • [COMMAND_EXECUTION]: Instructs the agent to perform actions using the belt CLI tool, including logging in and running inference applications.
  • [INDIRECT_PROMPT_INJECTION]: Processes external image URLs and prompt strings, which could serve as a vector for instructions if the sourced content is malicious. Ingestion points: image_url and prompt fields in SKILL.md. Boundary markers: Uses JSON structure for input data. Capability inventory: Uses the Bash tool to execute belt commands. Sanitization: No explicit sanitization or filtering is documented for the inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — background-removal