measuring-product-market-fit
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) as it is designed to ingest and process untrusted user data regarding business metrics and product segments.
- Ingestion points: Data enters the agent context through the primary prompt and the question bank in "references/INTAKE.md".
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within user data are present in "SKILL.md" or "references/WORKFLOW.md".
- Capability inventory: The skill is restricted to generating text reports and file-writing via standard agent tools; it lacks dangerous capabilities like eval() or direct shell execution.
- Sanitization: No input validation or sanitization logic is defined for the external data being processed.
- [NO_CODE]: This is a purely instructional skill consisting of Markdown guidelines, templates, and evaluation rubrics. It does not include Python, JavaScript, or shell scripts, which significantly limits the potential for direct code execution attacks.
- [SAFE]: No hardcoded credentials, sensitive file path access, persistence mechanisms, or unauthorized network exfiltration patterns were detected across the analyzed files.
Audit Metadata