ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to run image generation and editing tasks. Execution is scoped to the belt command through the allowed-tools configuration, minimizing risk from arbitrary shell execution.
  • [EXTERNAL_DOWNLOADS]: Instructions include installing the belt CLI via npx skills add belt-sh/cli and referencing related skills from the inference-sh organization. These represent standard setup procedures for the tool's ecosystem.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it interpolates user-provided text into the --input argument of shell commands.
  • Ingestion points: User-provided prompts and image URLs are passed to belt app run in SKILL.md examples.
  • Boundary markers: Absent; prompts are directly embedded in JSON strings.
  • Capability inventory: Uses Bash restricted to the belt command as defined in the frontmatter.
  • Sanitization: No explicit sanitization or validation of the input prompt is performed by the skill itself, relying on downstream model/service filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:03 PM
Security Audit — agent-trust-hub — ai-image-generation