product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to assist with marketing positioning and documentation. All described workflows and instructions are consistent with legitimate marketing tasks and project configuration management.
  • [COMMAND_EXECUTION]: The skill performs local file system operations, specifically reading repository metadata (README, package.json, and marketing assets) and writing a configuration file to .agents/product-marketing-context.md. These are routine operations for agents managing project context.
  • [PROMPT_INJECTION]: The skill includes an 'auto-draft' feature that ingests untrusted data from the local repository (e.g., scanning the README or landing page files), which presents a surface for indirect prompt injection.
    • Ingestion points: README, landing pages, marketing copy, and package.json (SKILL.md).
    • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are specified in the drafting process.
    • Capability inventory: The skill has the capability to read project files and write the marketing context document.
    • Sanitization: No sanitization or validation of the ingested repository content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 05:17 AM
Security Audit — agent-trust-hub — product-marketing-context