marketing-keyword-research
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of text-based instructions and methodologies. No malicious patterns, prompt injections, or unauthorized system access were detected.\n- [EXTERNAL_DOWNLOADS]: The skill references a GitHub repository (github.com/coreyhaines31/marketingskills) as a source for its methodology. This is a static reference to a third-party resource and does not involve automated script execution or package installation.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied seed keywords and business topics (SKILL.md, Step 1). While this constitutes an ingestion surface, the skill has no dangerous capabilities like shell execution, network exfiltration, or file writes. It lacks specific boundary markers for user input but includes a post-processing chain (ai-slop-reviewer) to refine and validate outputs.
Audit Metadata