Skills
skills/inference-sh-8/skills/background-removal/Gen Agent Trust Hub

background-removal

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation instructions and related skill modules from the inference-sh GitHub organization.
  • [COMMAND_EXECUTION]: Executes the infsh CLI tool to perform background removal and image editing operations.
  • [PROMPT_INJECTION]: The skill ingests untrusted data through image URLs and text prompts for editing tasks. While this presents an indirect prompt injection surface, the impact is limited by the tool's specific functionality.
  • Ingestion points: image_url and prompt fields in infsh app run commands within SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present.
  • Capability inventory: Access is restricted to the infsh tool via the allowed-tools configuration in SKILL.md.
  • Sanitization: No sanitization logic is visible in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:58 PM
Security Audit — agent-trust-hub — background-removal