background-removal

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install CLI tools and other skills from the inference-sh organization.
  • Evidence: Shell commands npx skills add belt-sh/cli and npx skills add inference-sh/skills@... are present in SKILL.md.
  • Context: These resources are provided by the official service associated with the skill's primary functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts external data in the form of image URLs and natural language prompts which are processed by a remote model, presenting a potential (though standard) injection surface.
  • Ingestion points: The image_url and prompt parameters used in belt app run commands within SKILL.md.
  • Boundary markers: None; inputs are passed directly to the tool's JSON input.
  • Capability inventory: The skill is restricted to running the belt CLI command via the Bash tool, as specified in the allowed-tools frontmatter.
  • Sanitization: None; the skill relies on the external service's API to handle content validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — background-removal