marketing-skills-collection

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: Data enters the agent context via the WebSearch and WebFetch tools used for competitor research and trend analysis, as well as through user-provided inputs in the marketing brief and product context sections.
  • Boundary markers: The instructions do not include delimiters or specific guidance to ignore embedded instructions within fetched or provided data.
  • Capability inventory: The skill is granted access to the Write, Read, WebSearch, WebFetch, and Task tools.
  • Sanitization: No sanitization or validation mechanisms are implemented to filter content retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:21 PM