rath-revenue-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown files and planning templates for marketing analysis. It does not contain any executable scripts, remote binary dependencies, or obfuscated instructions. All external references are to public informational content on LinkedIn and yoyaba.com, which are consistent with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data (CRM records and buyer research), creating a surface for indirect prompt injection. This is managed through the following evidence chain: 1. Ingestion points: Business context facts, CRM lifecycle data, and buyer research (SKILL.md steps 1, 4, and 5). 2. Boundary markers: Explicitly defined evidence boundaries in references/method.md and structured placeholders in templates/output-template.md. 3. Capability inventory: Analysis is limited to text generation and plan auditing; no shell execution, network exfiltration, or code evaluation tools are invoked by the skill logic. 4. Sanitization: The methodology utilizes a review checklist (checklists/review-checklist.md) to verify data integrity and fact discipline before final delivery.
Audit Metadata