cro
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to reference an external 'revops inbound-routing playbook' hosted at
https://github.com/coreyhaines31/marketingskills/blob/main/skills/revops/references/inbound-routing.md. As the source repository belongs to an unverified third-party user ('coreyhaines31'), this is identified as a reference to an untrusted external resource. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process and analyze content from marketing pages and lead forms provided by the user, creating a surface for indirect prompt injection.
- 1. Ingestion points: External URLs and content from marketing pages provided by the user for CRO analysis (SKILL.md).
- 2. Boundary markers: The instructions lack specific delimiters or system directives to isolate analyzed content or ignore embedded instructions within user-provided data.
- 3. Capability inventory: The skill generates complex recommendations and copy alternatives in natural language; while no dangerous system tools are explicitly requested, the analysis process itself acts on untrusted data.
- 4. Sanitization: No sanitization or input validation logic is present to filter malicious content retrieved from analyzed websites.
Audit Metadata