technical-blog-writing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the official GitHub repository for inference-sh. This is a trusted source used for legitimate setup procedures.
  • [COMMAND_EXECUTION]: Instructs the user to use the belt CLI tool and npx for managing skills and executing applications such as searching, image rendering, and social media posting.
  • [DYNAMIC_EXECUTION]: Includes a demonstration of a Python-based executor tool used to dynamically generate benchmark charts from code snippets provided within the skill.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Fetches external data from the web using the exa/search application to assist in blog research as shown in SKILL.md.
  • Boundary markers: The provided templates do not specify explicit delimiters or isolation instructions for processing search results.
  • Capability inventory: The skill has the ability to execute Python scripts, render HTML content into images, and interact with the X/Twitter API for distribution.
  • Sanitization: There is no explicit demonstration of sanitization or validation for the data ingested via the search tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:24 AM
Security Audit — agent-trust-hub — technical-blog-writing