product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate workflow for managing project-specific context. It helps maintain consistency by centralizing product and marketing information in a shared configuration file (.agents/product-marketing-context.md).- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its "Auto-draft" feature, which populates context from external and local sources.
  • Ingestion points: External project websites (landing pages, 'About Us' pages) and local codebase files (README.md) are read to draft the context file.
  • Boundary markers: The generated markdown template uses standard headers but lacks specific instructions for downstream agents to ignore potentially malicious instructions embedded within the user-provided marketing data.
  • Capability inventory: The skill writes a persistent configuration file to the local filesystem. Other skills in the marketing suite are explicitly instructed to read and follow the contents of this file before execution.
  • Sanitization: No automated sanitization is performed on the ingested text; however, the skill incorporates a manual review step where the user is asked to review and edit the draft before it is saved to disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 07:05 AM
Security Audit — agent-trust-hub — product-marketing-context