NYC

marketing-skills-collection

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill incorporates tools for ingesting external data, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: The skill utilizes WebSearch and WebFetch to gather product context and competitor information (e.g., in Example 3 for programmatic SEO).
  • Boundary markers: Absent. The instructions do not provide delimiters or specific guidelines for the agent to ignore instructions embedded within the fetched web content.
  • Capability inventory: Write, Read, WebSearch, WebFetch, Task. The skill does not have access to high-privilege system tools, sensitive environment variables, or arbitrary shell execution.
  • Sanitization: Absent. Data retrieved from the internet is interpolated into marketing prompts without formal sanitization or escaping instructions.
  • [No Code Detected] (SAFE): The skill is composed entirely of Markdown instructions and prompt templates. No Python, Node.js, or shell scripts are included, significantly reducing the attack surface for remote code execution or persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:19 PM