referrals

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest local project documentation to provide tailored marketing advice, which represents a standard context-gathering surface.
  • Ingestion points: The skill reads files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md from the local workspace.
  • Boundary markers: No explicit markers are used to delimit the external content, which is typical for internal project documentation ingestion.
  • Capability inventory: This is an informational skill that lacks dangerous executable capabilities, scripts, or network operation tools.
  • Sanitization: No sanitization is applied to the ingested marketing files as they are treated as trusted project context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 11:29 PM