landing-page-drafter

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch and read content from external competitor websites to inform the research and drafting process.
  • [COMMAND_EXECUTION]: Uses web browsing or fetch capabilities to access external URLs for market research.
  • [DATA_EXPOSURE]: Accesses local workspace files in the .sales/ directory, including value propositions and competitor lists, to generate context-aware marketing copy.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted content from external websites.
  • Ingestion points: Competitor landing pages fetched during the research phase (Step 2).
  • Boundary markers: No explicit instructions are provided to the agent to treat external content as untrusted data or to use delimiters.
  • Capability inventory: The skill performs file-write operations to .sales/landing-page-copy.md.
  • Sanitization: No sanitization or filtering of the external website content is described before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 06:11 PM
Security Audit — agent-trust-hub — landing-page-drafter