growth-hacker-seo
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions strictly focus on legitimate marketing tasks like keyword density analysis and meta-tag improvement, with no evidence of malicious intent, data exfiltration, or unauthorized command execution.
- [PROMPT_INJECTION]: The skill uses 'crawl_tool' to process external website content, which creates an inherent surface for indirect prompt injection. * Ingestion points: Target URLs fetched via 'crawl_tool' in SKILL.md. * Boundary markers: Absent; there are no specific instructions to delineate external content or to ignore potential directives embedded within the crawled sites. * Capability inventory: Limited to generating text-based SEO suggestions and keyword lists; no dangerous capabilities like shell access or file system modification are involved. * Sanitization: No explicit validation or sanitization of the fetched content is described in the instructions.
Audit Metadata