repo-website-guide-create

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of Markdown instructions, templates, and directory structure definitions. There are no scripts, binaries, or executable components included.
  • [COMMAND_EXECUTION] (SAFE): No shell commands, subprocess calls, or system-level operations are defined within the skill.
  • [DATA_EXFILTRATION] (SAFE): No network operations or hardcoded domains/IPs were found that could be used for data exfiltration.
  • [Indirect Prompt Injection] (LOW): The skill defines a workflow for creating files based on user-provided documentation topics.
  • Ingestion points: User-provided descriptions for schemas, pipelines, and tutorials entering the index.mdx files.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters to separate untrusted content from the template structure.
  • Capability inventory: File-write operations to website/src/routes/guides/ and file-append operations to menu.md (via the agent's file system tools).
  • Sanitization: Absent; the skill assumes the content for the guides will be safe for inclusion in the website's source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 02:42 PM