cro
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided marketing page content and URLs, which represents a potential ingestion surface for untrusted data.
- Ingestion points: Analysis of marketing pages, landing pages, and forms based on user-supplied URLs or descriptions as defined in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the analyzed content.
- Capability inventory: The skill has no associated scripts and does not utilize any tools for subprocess execution, file writing, or network operations.
- Sanitization: No input sanitization or validation routines are specified.
- [SAFE]: The skill relies on local reference files for context (e.g.,
references/form.md,references/experiments.md, and.agents/product-marketing.md), which is a secure and standard practice for internal knowledge management. - [SAFE]: No obfuscation, hardcoded credentials, or persistence mechanisms were detected in the skill instructions or reference documents.
Audit Metadata