create-gh-pages-site

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The helper scripts new-site.mjs and digest-repo.mjs execute local git commands (e.g., remote get-url, clone) to manage project configuration and template retrieval. These operations are essential to the skill's primary function of repository scaffolding.\n- [EXTERNAL_DOWNLOADS]: The skill retrieves website templates from the author's public repository (github.com/jongio/gh-pages-templates). This is a documented design choice for centralizing template management.\n- [PROMPT_INJECTION]: The skill processes natural language content from the target repository's README and documentation to automatically generate site content, creating an indirect prompt injection surface.\n
  • Ingestion points: SKILL.md directs the agent to read repository README files and documentation, which are subsequently processed by scripts/digest-repo.mjs.\n
  • Boundary markers: No specific delimiters or safety instructions are defined for the agent to distinguish between repository content and operational instructions.\n
  • Capability inventory: The skill allows the agent to write files to the workspace and execute Git commands via the included scripts.\n
  • Sanitization: The skill extracts structural elements (headings, code fences) but does not validate or sanitize the textual content for malicious instructions before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 03:35 AM
Security Audit — agent-trust-hub — create-gh-pages-site