keyword-research

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Keywords Everywhere MCP and user-provided domains, creating a potential surface for indirect prompt injection.
  • Ingestion points: Seed keywords, competitor domains, and data returned by the Keywords Everywhere MCP tools (Get Related Keywords, Get "People Also Search For" Keywords, Get Keyword Data, and Get Domain Keywords) as specified in SKILL.md.
  • Boundary markers: The instructions lack explicit boundary markers or specific instructions to ignore embedded commands within the processed data.
  • Capability inventory: The skill's capabilities are limited to data retrieval, clustering, scoring, and generating a markdown report. It does not perform file system writes, arbitrary shell command execution, or direct network operations.
  • Sanitization: No sanitization or validation of external content (keyword strings or domain data) is performed before it is interpolated into the final output report.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 03:07 PM