form-cro
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions specify that the agent should read external context files, specifically
.agents/product-marketing-context.mdor.claude/product-marketing-context.md, to inform its optimization recommendations. - Ingestion points: Identified in
SKILL.mdunder the 'Initial Assessment' section. - Boundary markers: None identified; the skill relies on the presence of these files for context without explicit delimiters for untrusted content.
- Capability inventory: The skill's primary functionality is providing textual audits and design advice. It does not include subprocess calls, network exfiltration, or file modification capabilities.
- Sanitization: No specific sanitization or validation of the ingested context file content is performed.
- [SAFE]: The skill metadata and instructional content do not contain any prompt injection attempts, obfuscated code, or unauthorized network operations. The focus remains entirely on conversion rate optimization best practices.
Audit Metadata