og-image-design

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from the inference-sh GitHub repository for CLI installation instructions.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the belt CLI tool and npx for generating images and managing dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where HTML content is processed to generate images, creating a potential surface for indirect prompt injection if untrusted data is interpolated into the HTML templates.
  • Ingestion points: HTML input strings within the belt app run infsh/html-to-image command parameters (SKILL.md).
  • Boundary markers: Absent; the examples show direct interpolation of text into HTML styles.
  • Capability inventory: Execution of shell commands via the Bash tool as specified in the skill's allowed-tools (SKILL.md).
  • Sanitization: No escaping or validation procedures are described for the HTML data being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:23 PM
Security Audit — agent-trust-hub — og-image-design