growth-engine
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of analyzing external data.
- Ingestion points: The skill ingests untrusted landing page content and SEO metadata provided by users via commands like /seo-analysis and /growth-audit in SKILL.md.
- Boundary markers: Absent; there are no specific markers or instructions to treat analyzed external content as data rather than instructions.
- Capability inventory: The skill is configured in the YAML frontmatter to use high-capability tools like claude-code and gemini-cli which have terminal and filesystem access.
- Sanitization: There is no evidence of sanitization or validation of the ingested content before it is processed by the AI agent.
Audit Metadata