keyword-cluster-builder
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, rules, and metadata. No executable code (Python, JavaScript, or shell scripts) is included in the package.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided data such as seed keywords, market descriptions, and content goals. This represents a standard surface for data processing; however, in the absence of executable logic or high-privilege tool chains, this presents no significant security risk.
- Ingestion points: User-supplied arguments defined in
SKILL.md(seed keyword, market, audience, and content goal). - Boundary markers: Not explicitly defined.
- Capability inventory: The skill is scoped to
ReadandWritetools only. - Sanitization: Standard LLM processing is used for text analysis without dynamic script execution.
Audit Metadata