product-marketing-context

Warn

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (MEDIUM): The skill is vulnerable to indirect prompt injection because it processes untrusted content from the repository to generate its outputs.
  • Ingestion points: Repository files such as README.md, package.json, and marketing documents are read during the auto-drafting phase in Step 2.
  • Boundary markers: None; the skill does not utilize delimiters or specific instructions to ignore embedded commands within the processed files.
  • Capability inventory: The skill can read arbitrary codebase files and write to '.claude/product-marketing-context.md'.
  • Sanitization: None; repo content is used directly for drafting without validation or filtering.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 05:32 AM