blog-writing-specialist

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh/python-executor tool to run dynamically generated Python code for creating benchmark charts. While the provided example uses matplotlib for legitimate visualization, this pattern involves generating and executing code at runtime.
  • [COMMAND_EXECUTION]: The skill employs infsh/html-to-image to render HTML and CSS into visual diagrams for architectural explanations.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process unstructured user data referred to as 'brain dumps' to generate blog posts, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided 'brain dump' text processed in Part 2 and Part 3 of SKILL.md.
  • Boundary markers: Absent. The skill does not specify delimiters or instructions for the agent to ignore commands potentially embedded within the user-provided content.
  • Capability inventory: The skill has access to tools for command execution (infsh/python-executor) and image generation.
  • Sanitization: Absent. There is no logic defined to sanitize or validate the content of the brain dump before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 02:34 PM