andy-raskin-strategic-narrative
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external business context and evidence provided by users for narrative generation.
- Ingestion points: The agent is instructed to gather buyer language and evidence from user-supplied inputs (SKILL.md, Step 2).
- Boundary markers: The skill provides a structured storyboard template with bracketed placeholders to organize and separate different narrative components (templates/output-template.md).
- Capability inventory: The skill's functions are limited to text analysis and drafting; it does not contain code execution, file system modifications, or network capabilities.
- Sanitization: A review checklist is included to verify that all claims are evidence-backed and to flag invented content or unsupported hypotheses (checklists/review-checklist.md).
Audit Metadata