keyword-research

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions provide a clear and secure workflow for SEO analysis using a specific set of tools for keyword discovery, metrics hydration, and search performance analysis.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or malicious persistence mechanisms was found. The skill operates within a controlled project context and utilizes standard authorization patterns (projectId).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input in the form of seed topics and audience problems to perform research.
  • Ingestion points: User-provided seed topics, product names, page URLs, and competitor lists in SKILL.md.
  • Boundary markers: None explicitly defined for user-supplied strings.
  • Capability inventory: Calls to external SEO research APIs (research_keywords, get_keyword_metrics, get_serp_results) and the ability to write project context and save keywords.
  • Sanitization: The skill includes a normalization step for seeds and a filtering step to remove irrelevant or off-intent terms, which mitigates the risk of processing malicious strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 07:35 PM
Security Audit — agent-trust-hub — keyword-research