create-portfolio

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script (scripts/validate-portfolio-frontmatter.js) to validate the frontmatter of generated portfolio files. This is a standard and expected use of project-specific tooling.\n- [PROMPT_INJECTION]: The skill ingests untrusted user data to populate Markdown templates, creating a surface for indirect prompt injection.\n
  • Ingestion points: User-supplied values for fields including title, client, description, challenges, solutions, outcomes, and metrics in SKILL.md.\n
  • Boundary markers: The instructions use YAML frontmatter and Markdown headers as structural delimiters to separate user data from instructions.\n
  • Capability inventory: The skill has capabilities to write files to the local file system (content/portfolio/) and execute a local Node.js validation script.\n
  • Sanitization: The skill includes basic validation for data formats (dates and URLs) via the script, though it does not explicitly define escaping for general string interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 08:15 PM
Security Audit — agent-trust-hub — create-portfolio